feat: record + analyze logprobs #1957
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Resolved conflicts between performance recording module implementation and empty file, keeping the full implementation. Also resolved conflicts in HTTP service tests to use proper API base configuration and service readiness checking. -Agent Generated Commit Message
WalkthroughThis change refactors stream and future type aliases across the LLM and runtime codebases to use a unified Changes
Sequence Diagram(s)sequenceDiagram
participant Test as Integration Test
participant Stream as RecordedStream
participant Analyzer as analyze_logprob_sensitivity
participant Result as SensitivityAnalysis
Test->>Stream: Generate synthetic or real streaming data
Test->>Analyzer: Call analyze_logprob_sensitivity(Stream)
Analyzer->>Stream: Extract logprobs per token/choice
Analyzer->>Analyzer: Compute closeness, greedy, and uncertainty stats
Analyzer-->>Result: Return SensitivityAnalysis
Test-->>Test: Assert on analysis results
Possibly related PRs
Poem
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (8)
lib/llm/tests/data/replays/deepseek-r1-distill-llama-8b/notes.md (1)
5-15: Specify language for fenced code block.The fenced code block should specify
bashorshellas the language for better syntax highlighting and documentation clarity.Apply this diff to specify the language:
-``` +```bash curl -X POST http://localhost:8000/v1/chat/completions \lib/runtime/tests/pipeline.rs (2)
16-16: Consider more targeted dead code allowances.Instead of applying
#![allow(dead_code)]at the crate level, consider using more targeted attributes on specific items that are temporarily unused.
205-257: Track the blocked test in an issue.The test is properly marked as ignored with a clear explanation. However, the large block of commented code (lines 240-254) should be removed and the blocking issue should be tracked in a GitHub issue for better visibility and follow-up.
Would you like me to create a GitHub issue to track the resolution of this
AsyncEngineStream+Synctrait bound mismatch?lib/runtime/tests/common/mock.rs (1)
16-16: Consider more targeted dead code allowances.Similar to the other test file, using
#![allow(dead_code)]at the crate level is overly broad for test utilities.lib/llm/tests/logprob_analysis_integration.rs (1)
149-149: Consider making the performance assertion more flexible.The hardcoded 100ms threshold could cause flaky tests in CI environments or under heavy load. Consider either increasing the threshold or making it configurable based on the environment.
- assert!(elapsed.as_millis() < 100); + // Allow more time in CI/debug builds + let max_millis = if cfg!(debug_assertions) { 500 } else { 100 }; + assert!(elapsed.as_millis() < max_millis, "Analysis took {}ms, expected < {}ms", elapsed.as_millis(), max_millis);lib/llm/src/perf/logprobs.rs (3)
142-155: Remove unusedClosePositionstruct.The
ClosePositionstruct appears to be unused in the codebase and is redundant withPositionCloseness. Consider removing it to reduce code clutter.
95-95: Consider safer handling of float comparisons.While logprobs should be finite values, using
unwrap()onpartial_cmpcould panic if NaN values are encountered. Consider usingunwrap_orwith a default ordering or explicitly handling the None case.- top_alternatives - .sort_by(|a, b| b.logprob.partial_cmp(&a.logprob).unwrap()); + top_alternatives + .sort_by(|a, b| b.logprob.partial_cmp(&a.logprob).unwrap_or(std::cmp::Ordering::Equal));Also applies to: 186-186, 213-215
346-358: Document or make configurable the greedy detection thresholds.The thresholds 0.01 and 0.05 for greedy detection appear to be magic numbers. Consider extracting them as named constants with documentation explaining the rationale, or making them configurable.
+ /// Threshold for considering tokens as tied (very close in probability) + const GREEDY_TIE_THRESHOLD: f32 = 0.01; + /// Threshold for considering a token as a clear winner + const GREEDY_CLEAR_WINNER_THRESHOLD: f32 = 0.05; + /// Detect if greedy decoding was likely used by checking if selected tokens are always the most probable /// Note: This is an approximation since we infer selection from the data structure pub fn detect_likely_greedy_decoding(&self, choice_index: usize) -> bool { // ... existing code ... // Either very close (tie - could be greedy) or clear difference (likely greedy) - pos.probability_difference < 0.01 || pos.probability_difference > 0.05 + pos.probability_difference < Self::GREEDY_TIE_THRESHOLD || pos.probability_difference > Self::GREEDY_CLEAR_WINNER_THRESHOLDAlso applies to: 375-381
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
Cargo.lockis excluded by!**/*.lock
📒 Files selected for processing (19)
lib/llm/Cargo.toml(1 hunks)lib/llm/src/http/client.rs(4 hunks)lib/llm/src/perf.rs(2 hunks)lib/llm/src/perf/logprobs.rs(1 hunks)lib/llm/src/protocols.rs(2 hunks)lib/llm/src/protocols/openai/chat_completions/aggregator.rs(1 hunks)lib/llm/src/protocols/openai/embeddings/aggregator.rs(1 hunks)lib/llm/tests/data/replays/deepseek-r1-distill-llama-8b/notes.md(1 hunks)lib/llm/tests/logprob_analysis_integration.rs(1 hunks)lib/runtime/src/engine.rs(4 hunks)lib/runtime/src/pipeline.rs(2 hunks)lib/runtime/src/pipeline/network.rs(1 hunks)lib/runtime/src/pipeline/nodes.rs(2 hunks)lib/runtime/src/pipeline/nodes/sinks/pipeline.rs(1 hunks)lib/runtime/src/pipeline/nodes/sinks/segment.rs(1 hunks)lib/runtime/src/pipeline/nodes/sources/base.rs(1 hunks)lib/runtime/src/pipeline/nodes/sources/common.rs(1 hunks)lib/runtime/tests/common/mock.rs(2 hunks)lib/runtime/tests/pipeline.rs(3 hunks)
🧰 Additional context used
🧠 Learnings (17)
📓 Common learnings
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
lib/llm/src/protocols/openai/embeddings/aggregator.rs (2)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
Learnt from: t-ob
PR: ai-dynamo/dynamo#1290
File: launch/dynamo-run/src/subprocess/sglang_inc.py:80-110
Timestamp: 2025-06-03T10:17:51.711Z
Learning: The sglang `async_encode` method does not support streaming options, so collecting all embeddings before yielding is the correct approach for embedding requests.
lib/llm/src/perf.rs (1)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
lib/runtime/src/pipeline/nodes/sinks/pipeline.rs (1)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
lib/runtime/src/pipeline/network.rs (1)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
lib/runtime/src/pipeline/nodes/sources/common.rs (1)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
lib/llm/src/protocols.rs (2)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
Learnt from: kthui
PR: ai-dynamo/dynamo#1424
File: lib/runtime/src/pipeline/network/egress/push_router.rs:204-209
Timestamp: 2025-06-13T22:07:24.843Z
Learning: The codebase uses async-nats version 0.40, not the older nats crate. Error handling should use async_nats::error::Error variants, not nats::Error variants.
lib/runtime/src/pipeline/nodes/sinks/segment.rs (1)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
lib/llm/src/protocols/openai/chat_completions/aggregator.rs (1)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
lib/runtime/tests/pipeline.rs (4)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1093
File: lib/llm/src/block_manager/block/registry.rs:98-122
Timestamp: 2025-05-29T06:20:12.901Z
Learning: In lib/llm/src/block_manager/block/registry.rs, the background task spawned for handling unregister notifications uses detached concurrency by design. The JoinHandle is intentionally not stored as this represents a reasonable architectural tradeoff for a long-running cleanup task.
Learnt from: PeaBrane
PR: ai-dynamo/dynamo#1236
File: lib/llm/src/mocker/engine.rs:140-161
Timestamp: 2025-06-17T00:50:44.845Z
Learning: In Rust async code, when an Arc<Mutex<_>> is used solely to transfer ownership of a resource (like a channel receiver) into a spawned task rather than for sharing between multiple tasks, holding the mutex lock across an await is not problematic since there's no actual contention.
Learnt from: oandreeva-nv
PR: ai-dynamo/dynamo#1195
File: lib/llm/tests/block_manager.rs:150-152
Timestamp: 2025-06-02T19:37:27.666Z
Learning: In Rust/Tokio applications, when background tasks use channels for communication, dropping the sender automatically signals task termination when the receiver gets `None`. The `start_batching_publisher` function in `lib/llm/tests/block_manager.rs` demonstrates this pattern: when the `KVBMDynamoRuntimeComponent` is dropped, its `batch_tx` sender is dropped, causing `rx.recv()` to return `None`, which triggers cleanup and task termination.
lib/runtime/src/pipeline/nodes/sources/base.rs (2)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
Learnt from: kthui
PR: ai-dynamo/dynamo#1424
File: lib/runtime/src/pipeline/network/egress/push_router.rs:204-209
Timestamp: 2025-06-13T22:07:24.843Z
Learning: The codebase uses async-nats version 0.40, not the older nats crate. Error handling should use async_nats::error::Error variants, not nats::Error variants.
lib/runtime/src/pipeline/nodes.rs (2)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
Learnt from: kthui
PR: ai-dynamo/dynamo#1424
File: lib/runtime/src/pipeline/network/egress/push_router.rs:204-209
Timestamp: 2025-06-13T22:07:24.843Z
Learning: The codebase uses async-nats version 0.40, not the older nats crate. Error handling should use async_nats::error::Error variants, not nats::Error variants.
lib/runtime/tests/common/mock.rs (5)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
Learnt from: kthui
PR: ai-dynamo/dynamo#1424
File: lib/runtime/src/pipeline/network/egress/push_router.rs:204-209
Timestamp: 2025-06-13T22:07:24.843Z
Learning: The codebase uses async-nats version 0.40, not the older nats crate. Error handling should use async_nats::error::Error variants, not nats::Error variants.
Learnt from: PeaBrane
PR: ai-dynamo/dynamo#1236
File: lib/llm/src/mocker/engine.rs:140-161
Timestamp: 2025-06-17T00:50:44.845Z
Learning: In Rust async code, when an Arc<Mutex<_>> is used solely to transfer ownership of a resource (like a channel receiver) into a spawned task rather than for sharing between multiple tasks, holding the mutex lock across an await is not problematic since there's no actual contention.
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1093
File: lib/llm/src/block_manager/block/registry.rs:98-122
Timestamp: 2025-05-29T06:20:12.901Z
Learning: In lib/llm/src/block_manager/block/registry.rs, the background task spawned for handling unregister notifications uses detached concurrency by design. The JoinHandle is intentionally not stored as this represents a reasonable architectural tradeoff for a long-running cleanup task.
Learnt from: oandreeva-nv
PR: ai-dynamo/dynamo#1195
File: lib/llm/tests/block_manager.rs:150-152
Timestamp: 2025-06-02T19:37:27.666Z
Learning: In Rust/Tokio applications, when background tasks use channels for communication, dropping the sender automatically signals task termination when the receiver gets `None`. The `start_batching_publisher` function in `lib/llm/tests/block_manager.rs` demonstrates this pattern: when the `KVBMDynamoRuntimeComponent` is dropped, its `batch_tx` sender is dropped, causing `rx.recv()` to return `None`, which triggers cleanup and task termination.
lib/runtime/src/pipeline.rs (1)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
lib/runtime/src/engine.rs (2)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
Learnt from: kthui
PR: ai-dynamo/dynamo#1424
File: lib/runtime/src/pipeline/network/egress/push_router.rs:204-209
Timestamp: 2025-06-13T22:07:24.843Z
Learning: The codebase uses async-nats version 0.40, not the older nats crate. Error handling should use async_nats::error::Error variants, not nats::Error variants.
lib/llm/src/http/client.rs (2)
Learnt from: ryanolson
PR: ai-dynamo/dynamo#1919
File: lib/runtime/src/engine.rs:168-168
Timestamp: 2025-07-14T21:25:56.898Z
Learning: The AsyncEngineContextProvider trait in lib/runtime/src/engine.rs was intentionally changed from `Send + Sync + Debug` to `Send + Debug` because the Sync bound was overly constraining. The trait should only require Send + Debug as designed.
Learnt from: PeaBrane
PR: ai-dynamo/dynamo#1236
File: lib/llm/src/mocker/engine.rs:140-161
Timestamp: 2025-06-17T00:50:44.845Z
Learning: In Rust async code, when an Arc<Mutex<_>> is used solely to transfer ownership of a resource (like a channel receiver) into a spawned task rather than for sharing between multiple tasks, holding the mutex lock across an await is not problematic since there's no actual contention.
lib/llm/src/perf/logprobs.rs (1)
Learnt from: ishandhanani
PR: ai-dynamo/dynamo#1626
File: lib/llm/src/preprocessor.rs:238-239
Timestamp: 2025-06-24T20:59:35.725Z
Learning: In lib/llm/src/preprocessor.rs, the `sampling_options` call in the `preprocess_request` method is placed in the common section after the match statement on `request.prompt_input_type()`, meaning it applies to both `PromptInput::Tokens` and `PromptInput::Text` request types.
🧬 Code Graph Analysis (2)
lib/llm/src/http/client.rs (1)
lib/runtime/src/engine.rs (7)
new(225-227)context(169-169)context(245-247)context(262-264)context(268-270)context(443-446)context(458-460)
lib/llm/src/perf/logprobs.rs (3)
lib/runtime/tests/common/mock.rs (2)
new(149-156)new(297-303)lib/llm/src/perf.rs (16)
new(43-49)new(97-107)new(515-519)record_stream_with_context(284-293)start_time(125-127)responses(120-122)data(52-54)response_count(110-112)id(524-526)stop(528-530)stop_generating(532-534)kill(536-538)is_stopped(540-542)is_killed(544-546)stopped(548-550)killed(552-554)lib/llm/src/protocols/codec.rs (1)
create_message_stream(296-302)
🪛 markdownlint-cli2 (0.17.2)
lib/llm/tests/data/replays/deepseek-r1-distill-llama-8b/notes.md
5-5: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)
- GitHub Check: Build and Test - vllm
- GitHub Check: pre-merge-rust (lib/runtime/examples)
- GitHub Check: pre-merge-rust (lib/bindings/python)
- GitHub Check: pre-merge-rust (.)
🔇 Additional comments (20)
lib/llm/Cargo.toml (1)
132-132: LGTM! Appropriate dependency for logprob analysis testing.The
approxcrate is well-suited for floating-point comparisons in logprob analysis tests, providing tolerance-based equality checks for numerical computations.lib/runtime/src/pipeline/nodes/sinks/segment.rs (1)
41-41: LGTM! Consistent with pipeline concurrency requirements.The addition of the
Syncbound toReqaligns with the broader refactoring pattern to ensure thread safety for pipeline components while maintaining flexibility where appropriate.lib/llm/src/protocols/openai/embeddings/aggregator.rs (1)
22-23: LGTM! Stream type consolidation improves consistency.The centralized
DataStreamimport fromdynamo_runtime::engineeliminates duplicate type definitions and ensures uniform stream abstractions across the codebase.lib/runtime/src/pipeline/network.rs (1)
283-283: LGTM! Enforces thread safety for pipeline ingress operations.The
Syncbound addition ensures safe concurrent access to request data, maintaining consistency with the pipeline's concurrency requirements.lib/llm/src/perf.rs (2)
9-9: LGTM! New logprob analysis module aligns with PR objectives.The public
logprobsmodule provides the infrastructure for log probability recording and analysis functionality as intended by this PR.
344-344: LGTM! Public test module supports integration testing.Making the tests public likely enables access to test utilities for logprob analysis functionality across the codebase.
lib/runtime/src/pipeline/nodes/sinks/pipeline.rs (1)
29-29: LGTM! Consistent trait bound refinement.The addition of the
Syncbound to theReqparameter aligns with the coordinated refactoring effort to strengthen concurrency guarantees for pipeline input types across the codebase.lib/llm/src/protocols/openai/chat_completions/aggregator.rs (1)
27-27: LGTM! Relaxing stream synchronization constraints.Removing the
Syncbound from theDataStreamtype alias is consistent with the broader refactoring effort to avoid over-constraining asynchronous streams while maintaining necessary thread safety guarantees.lib/llm/src/protocols.rs (2)
22-22: Good import cleanup.Removing the unused imports
std::pin::Pinandfutures::Streamsince the localDataStreamtype alias has been replaced by the centralized re-export.
31-31: Excellent centralization of DataStream type.Re-exporting
DataStreamfromdynamo_runtime::engineeliminates type alias duplication and ensures consistent stream type definitions across the codebase.lib/runtime/src/pipeline/nodes/sources/common.rs (1)
51-53: LGTM! Consistent pipeline input type constraints.Adding the
Syncbound to theInparameter strengthens concurrency guarantees for pipeline operations, consistent with the coordinated trait bound refinement across the runtime pipeline modules.lib/runtime/src/pipeline/nodes/sources/base.rs (1)
71-71: LGTM! Appropriate addition ofSyncbound.The addition of the
Syncbound to theInparameter is consistent with the broader pattern of strengthening concurrency guarantees for pipeline IO types across the runtime module.lib/runtime/src/pipeline.rs (1)
72-72: Good architectural improvement in trait bound organization.Moving the
Dataconstraint fromPipelineIOtoAsyncTransportEngineprovides better flexibility. This allowsPipelineIOto be implemented by types that don't need fullDatacapabilities, while ensuring transport engines have the necessary constraints.Also applies to: 100-100
lib/runtime/src/pipeline/nodes.rs (1)
224-225: LGTM! ConsistentSyncbounds for pipeline operators.The addition of
Syncbounds toUpInandDownInparameters ensures thread-safety for pipeline operators and is consistent with similar changes across the pipeline module.Also applies to: 238-239
lib/runtime/tests/common/mock.rs (2)
164-165: Appropriate trait bounds for async engine implementation.The added
Send + Sync + 'staticbounds onUandSend + SynconSelfare necessary for proper async engine implementation in concurrent contexts.
252-270: Excellent refactoring of stream processing logic.The use of the
scancombinator withResponseMonitorprovides clean stateful stream processing. The handling of heartbeat and sentinel headers is now more explicit and maintainable.lib/runtime/src/engine.rs (1)
95-96: Appropriate removal of overly constrainingSyncbounds.The removal of
Syncbounds fromDataUnary,DataStream,AsyncEngineUnary, andAsyncEngineStreamis correct and aligns with the established pattern. Futures and streams typically only requireSendfor cross-thread usage, notSync.The change to
AsyncEnginetrait bounds is also appropriate - making theSend + Sync + 'staticrequirement explicit forReqwhile removing the unnecessaryDataconstraint fromResp.Also applies to: 177-177, 186-186, 207-207
lib/llm/src/http/client.rs (1)
306-308: Good removal of unsafeSyncimplementation.Removing this unsafe implementation is the right decision. Since
AsyncEngineStreamno longer requiresSync, there's no need to unsafely claim that the wrapper isSyncwhen the underlying stream might not be.lib/llm/tests/logprob_analysis_integration.rs (1)
340-350: Excellent probability distribution validation.The validation ensures that probabilities are in the [0, 1] range and that the total probability mass doesn't exceed 1.0, which is mathematically correct for a probability distribution. The small epsilon allowance for floating-point errors is also appropriate.
Also applies to: 419-429
lib/llm/src/perf/logprobs.rs (1)
189-195: Excellent design choice converting to probability space.Converting logprob differences to probability space (linear scale) makes the closeness values much more intuitive to interpret. A difference of 0.1 in probability space is easier to understand than the equivalent logprob difference.
grahamking
approved these changes
Jul 17, 2025
ZichengMa
pushed a commit
that referenced
this pull request
Jul 17, 2025
ZichengMa
added a commit
that referenced
this pull request
Jul 18, 2025
commit e330d96 Author: Yan Ru Pei <yanrpei@gmail.com> Date: Fri Jul 18 13:40:54 2025 -0700 feat: enable / disable chunked prefill for mockers (#2015) Signed-off-by: Yan Ru Pei <yanrpei@gmail.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> commit 353146e Author: GuanLuo <41310872+GuanLuo@users.noreply.github.com> Date: Fri Jul 18 13:33:36 2025 -0700 feat: add vLLM v1 multi-modal example. Add llama4 Maverick example (#1990) Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com> Co-authored-by: krishung5 <krish@nvidia.com> commit 1f07dab Author: Jacky <18255193+kthui@users.noreply.github.com> Date: Fri Jul 18 13:04:20 2025 -0700 feat: Add migration to LLM requests (#1930) commit 5f17918 Author: Tanmay Verma <tanmayv@nvidia.com> Date: Fri Jul 18 12:59:34 2025 -0700 refactor: Migrate to new UX2 for python launch (#2003) commit fc12436 Author: Graham King <grahamk@nvidia.com> Date: Fri Jul 18 14:52:57 2025 -0400 feat(frontend): router-mode settings (#2001) commit dc75cf1 Author: ptarasiewiczNV <104908264+ptarasiewiczNV@users.noreply.github.com> Date: Fri Jul 18 18:47:28 2025 +0200 chore: Move NIXL repo clone to Dockerfiles (#2009) commit f6f392c Author: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com> Date: Thu Jul 17 18:44:17 2025 -0700 Remove link to the fix for disagg + eagle3 for TRT-LLM example (#2006) Signed-off-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com> commit cc90ca6 Author: atchernych <atchernych@nvidia.com> Date: Thu Jul 17 18:34:40 2025 -0700 feat: Create a convenience script to uninstall Dynamo Deploy CRDs (#1933) commit 267b422 Author: Greg Clark <grclark@nvidia.com> Date: Thu Jul 17 20:44:21 2025 -0400 chore: loosed python requirement versions (#1998) Signed-off-by: Greg Clark <grclark@nvidia.com> commit b8474e5 Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Thu Jul 17 16:35:05 2025 -0700 chore: update cmake and gap installation and sgl in wideep container (#1991) commit 157a3b0 Author: Biswa Panda <biswa.panda@gmail.com> Date: Thu Jul 17 15:38:12 2025 -0700 fix: incorrect helm upgrade command (#2000) commit 0dfca2c Author: Ryan McCormick <rmccormick@nvidia.com> Date: Thu Jul 17 15:33:33 2025 -0700 ci: Update trtllm gitlab triggers for new components directory and test script (#1992) commit f3fb09e Author: Kris Hung <krish@nvidia.com> Date: Thu Jul 17 14:59:59 2025 -0700 fix: Fix syntax for tokio-console (#1997) commit dacffb8 Author: Biswa Panda <biswa.panda@gmail.com> Date: Thu Jul 17 14:57:10 2025 -0700 fix: use non-dev golang image for operator (#1993) commit 2b29a0a Author: zaristei <zaristei@berkeley.edu> Date: Thu Jul 17 13:10:42 2025 -0700 fix: Working Arm Build Dockerfile for Vllm_v1 (#1844) commit 2430d89 Author: Ryan McCormick <rmccormick@nvidia.com> Date: Thu Jul 17 12:57:46 2025 -0700 test: Add trtllm kv router tests (#1988) commit 1eadc01 Author: Graham King <grahamk@nvidia.com> Date: Thu Jul 17 15:07:41 2025 -0400 feat(runtime): Support tokio-console (#1986) commit b62e633 Author: GuanLuo <41310872+GuanLuo@users.noreply.github.com> Date: Thu Jul 17 11:16:28 2025 -0700 feat: support separate chat_template.jinja file (#1853) commit 8ae3719 Author: Hongkuan Zhou <tedzhouhk@gmail.com> Date: Thu Jul 17 11:12:35 2025 -0700 chore: add some details to dynamo deploy quickstart and fix deploy.sh (#1978) Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com> Co-authored-by: julienmancuso <161955438+julienmancuso@users.noreply.github.com> commit 08891ff Author: Ryan McCormick <rmccormick@nvidia.com> Date: Thu Jul 17 10:57:42 2025 -0700 fix: Update trtllm tests to use new scripts instead of dynamo serve (#1979) commit 49b7a0d Author: Ryan Olson <ryanolson@users.noreply.github.com> Date: Thu Jul 17 08:35:04 2025 -0600 feat: record + analyze logprobs (#1957) commit 6d2be14 Author: Biswa Panda <biswa.panda@gmail.com> Date: Thu Jul 17 00:17:58 2025 -0700 refactor: replace vllm with vllm_v1 container (#1953) Co-authored-by: alec-flowers <aflowers@nvidia.com> commit 4d2a31a Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Wed Jul 16 18:04:09 2025 -0700 chore: add port reservation to utils (#1980) commit 1e3e4a0 Author: Alec <35311602+alec-flowers@users.noreply.github.com> Date: Wed Jul 16 15:54:04 2025 -0700 fix: port race condition through deterministic ports (#1937) commit 4ad281f Author: Tanmay Verma <tanmayv@nvidia.com> Date: Wed Jul 16 14:33:51 2025 -0700 refactor: Move TRTLLM example to the component/backends (#1976) commit 57d24a1 Author: Misha Chornyi <99709299+mc-nv@users.noreply.github.com> Date: Wed Jul 16 14:10:24 2025 -0700 build: Removing shell configuration violations. It's bad practice to hardcod… (#1973) commit 182d3b5 Author: Graham King <grahamk@nvidia.com> Date: Wed Jul 16 16:12:40 2025 -0400 chore(bindings): Remove mistralrs / llama.cpp (#1970) commit def6eaa Author: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com> Date: Wed Jul 16 15:50:23 2025 -0400 feat: attributions for debian deps of sglang, trtllm, vllm runtime containers (#1971) commit f31732a Author: Yan Ru Pei <yanrpei@gmail.com> Date: Wed Jul 16 11:22:15 2025 -0700 feat: integrate mocker with dynamo-run and python cli (#1927) commit aba6099 Author: Graham King <grahamk@nvidia.com> Date: Wed Jul 16 12:26:32 2025 -0400 perf(router): Remove lock from router hot path (#1963) commit b212103 Author: Hongkuan Zhou <tedzhouhk@gmail.com> Date: Wed Jul 16 08:55:33 2025 -0700 docs: add notes in docs to deprecate local connector (#1959) commit 7b325ee Author: Biswa Panda <biswa.panda@gmail.com> Date: Tue Jul 15 18:52:00 2025 -0700 fix: vllm router examples (#1942) commit a50be1a Author: hhzhang16 <54051230+hhzhang16@users.noreply.github.com> Date: Tue Jul 15 17:58:01 2025 -0700 feat: update CODEOWNERS (#1926) commit e260fdf Author: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com> Date: Tue Jul 15 18:49:21 2025 -0400 feat: add bitnami helm chart attribution (#1943) Signed-off-by: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> commit 1c03404 Author: Biswa Panda <biswa.panda@gmail.com> Date: Tue Jul 15 14:26:24 2025 -0700 fix: update inference gateway deployment instructions (#1940) commit 5ca570f Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 16:54:03 2025 -0400 chore: Rename dynamo.ingress to dynamo.frontend (#1944) commit 7b9182f Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 16:33:07 2025 -0400 chore: Move examples/cli to lib/bindings/examples/cli (#1952) commit 40d40dd Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 16:02:19 2025 -0400 chore(multi-modal): Rename frontend.py to web.py (#1951) commit a9e0891 Author: Ryan Olson <ryanolson@users.noreply.github.com> Date: Tue Jul 15 12:30:30 2025 -0600 feat: adding http clients and recorded response stream (#1919) commit 4128d58 Author: Biswa Panda <biswa.panda@gmail.com> Date: Tue Jul 15 10:30:47 2025 -0700 feat: allow helm upgrade using deploy script (#1936) commit 4da078b Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 12:57:38 2025 -0400 fix: Remove OpenSSL dependency, use Rust TLS (#1945) commit fc004d4 Author: jthomson04 <jwillthomson19@gmail.com> Date: Tue Jul 15 08:45:42 2025 -0700 fix: Fix TRT-LLM container build when using a custom pip wheel (#1825) commit 3c6fc6f Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Mon Jul 14 22:35:20 2025 -0700 chore: fix typo (#1938) commit de7fe38 Author: Alec <35311602+alec-flowers@users.noreply.github.com> Date: Mon Jul 14 21:47:12 2025 -0700 feat: add vllm e2e integration tests (#1935) commit 860f3f7 Author: Keiven C <213854356+keivenchang@users.noreply.github.com> Date: Mon Jul 14 21:44:19 2025 -0700 chore: metrics endpoint variables renamed from HTTP_SERVER->SYSTEM (#1934) Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com> commit fc402a3 Author: Biswa Panda <biswa.panda@gmail.com> Date: Mon Jul 14 21:21:20 2025 -0700 feat: configurable namespace for vllm v1 example (#1909) commit df40d2c Author: ZichengMa <zichengma1225@gmail.com> Date: Mon Jul 14 21:11:29 2025 -0700 docs: fix typo and add mount-workspace to vllm doc (#1931) Signed-off-by: ZichengMa <zichengma1225@gmail.com> Co-authored-by: Alec <35311602+alec-flowers@users.noreply.github.com> commit 901715b Author: Tanmay Verma <tanmayv@nvidia.com> Date: Mon Jul 14 20:14:51 2025 -0700 refactor: Refactor the TRTLLM examples remove dynamo SDK (#1884) commit 5bf23d5 Author: hhzhang16 <54051230+hhzhang16@users.noreply.github.com> Date: Mon Jul 14 18:29:19 2025 -0700 feat: update DynamoGraphDeployments for vllm_v1 (#1890) Co-authored-by: mohammedabdulwahhab <furkhan324@berkeley.edu> commit 9e76590 Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Mon Jul 14 17:29:56 2025 -0700 docs: organize sglang readme (#1910) commit ef59ac8 Author: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com> Date: Mon Jul 14 16:16:44 2025 -0700 docs: TRTLLM Example of Llama4+Eagle3 (Speculative Decoding) (#1828) Signed-off-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com> Co-authored-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com> commit 053041e Author: Jorge António <matroid@outlook.com> Date: Tue Jul 15 00:06:38 2025 +0100 fix: resolve incorrect finish reason propagation (#1857) commit 3733f58 Author: Graham King <grahamk@nvidia.com> Date: Mon Jul 14 19:04:22 2025 -0400 feat(backends): Python llama.cpp engine (#1925) commit 6a1350c Author: Tushar Sharma <tusharma@nvidia.com> Date: Mon Jul 14 14:56:36 2025 -0700 build: minor improvements to sglang dockerfile (#1917) commit e2a619b Author: Neelay Shah <neelays@nvidia.com> Date: Mon Jul 14 14:52:53 2025 -0700 fix: remove environment variable passing (#1911) Signed-off-by: Neelay Shah <neelays@nvidia.com> Co-authored-by: Neelay Shah <neelays@a4u8g-0057.ipp2u2.colossus.nvidia.com> commit 3d17a49 Author: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com> Date: Mon Jul 14 14:41:56 2025 -0700 refactor: remove dynamo build (#1778) Signed-off-by: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com> commit 3e0cb07 Author: Anant Sharma <anants@nvidia.com> Date: Mon Jul 14 15:43:48 2025 -0400 fix: copy attributions and license to trtllm runtime container (#1916) commit fc36bf5 Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Mon Jul 14 12:31:49 2025 -0700 feat: receive kvmetrics from sglang scheduler (#1789) Co-authored-by: zixuanzhang226 <zixuanzhang@bytedance.com> commit df91fce Author: Yan Ru Pei <yanrpei@gmail.com> Date: Mon Jul 14 12:24:04 2025 -0700 feat: prefill aware routing (#1895) commit ad8ad66 Author: Graham King <grahamk@nvidia.com> Date: Mon Jul 14 15:20:35 2025 -0400 feat: Shrink the ai-dynamo wheel by 35 MiB (#1918) Remove http and llmctl binaries. They have been unused for a while. commit 480b41d Author: Graham King <grahamk@nvidia.com> Date: Mon Jul 14 15:06:45 2025 -0400 feat: Python frontend / ingress node (#1912)
ZichengMa
added a commit
that referenced
this pull request
Jul 21, 2025
commit cb6de94 Author: ptarasiewiczNV <104908264+ptarasiewiczNV@users.noreply.github.com> Date: Sun Jul 20 22:34:50 2025 +0200 chore: Install vLLM and WideEP kernels in vLLM runtime container (#2010) Signed-off-by: Alec <35311602+alec-flowers@users.noreply.github.com> Co-authored-by: Alec <35311602+alec-flowers@users.noreply.github.com> Co-authored-by: alec-flowers <aflowers@nvidia.com> commit fe63c17 Author: Alec <35311602+alec-flowers@users.noreply.github.com> Date: Fri Jul 18 17:45:08 2025 -0700 fix: Revert "feat: add vLLM v1 multi-modal example. Add llama4 Maverick ex… (#2017) commit bf1998f Author: jthomson04 <jwillthomson19@gmail.com> Date: Fri Jul 18 17:23:50 2025 -0700 fix: Don't detokenize twice in TRT-LLM examples (#1955) commit 343a481 Author: Ryan Olson <ryanolson@users.noreply.github.com> Date: Fri Jul 18 16:22:43 2025 -0600 feat: http disconnects (#2014) commit e330d96 Author: Yan Ru Pei <yanrpei@gmail.com> Date: Fri Jul 18 13:40:54 2025 -0700 feat: enable / disable chunked prefill for mockers (#2015) Signed-off-by: Yan Ru Pei <yanrpei@gmail.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> commit 353146e Author: GuanLuo <41310872+GuanLuo@users.noreply.github.com> Date: Fri Jul 18 13:33:36 2025 -0700 feat: add vLLM v1 multi-modal example. Add llama4 Maverick example (#1990) Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com> Co-authored-by: krishung5 <krish@nvidia.com> commit 1f07dab Author: Jacky <18255193+kthui@users.noreply.github.com> Date: Fri Jul 18 13:04:20 2025 -0700 feat: Add migration to LLM requests (#1930) commit 5f17918 Author: Tanmay Verma <tanmayv@nvidia.com> Date: Fri Jul 18 12:59:34 2025 -0700 refactor: Migrate to new UX2 for python launch (#2003) commit fc12436 Author: Graham King <grahamk@nvidia.com> Date: Fri Jul 18 14:52:57 2025 -0400 feat(frontend): router-mode settings (#2001) commit dc75cf1 Author: ptarasiewiczNV <104908264+ptarasiewiczNV@users.noreply.github.com> Date: Fri Jul 18 18:47:28 2025 +0200 chore: Move NIXL repo clone to Dockerfiles (#2009) commit f6f392c Author: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com> Date: Thu Jul 17 18:44:17 2025 -0700 Remove link to the fix for disagg + eagle3 for TRT-LLM example (#2006) Signed-off-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com> commit cc90ca6 Author: atchernych <atchernych@nvidia.com> Date: Thu Jul 17 18:34:40 2025 -0700 feat: Create a convenience script to uninstall Dynamo Deploy CRDs (#1933) commit 267b422 Author: Greg Clark <grclark@nvidia.com> Date: Thu Jul 17 20:44:21 2025 -0400 chore: loosed python requirement versions (#1998) Signed-off-by: Greg Clark <grclark@nvidia.com> commit b8474e5 Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Thu Jul 17 16:35:05 2025 -0700 chore: update cmake and gap installation and sgl in wideep container (#1991) commit 157a3b0 Author: Biswa Panda <biswa.panda@gmail.com> Date: Thu Jul 17 15:38:12 2025 -0700 fix: incorrect helm upgrade command (#2000) commit 0dfca2c Author: Ryan McCormick <rmccormick@nvidia.com> Date: Thu Jul 17 15:33:33 2025 -0700 ci: Update trtllm gitlab triggers for new components directory and test script (#1992) commit f3fb09e Author: Kris Hung <krish@nvidia.com> Date: Thu Jul 17 14:59:59 2025 -0700 fix: Fix syntax for tokio-console (#1997) commit dacffb8 Author: Biswa Panda <biswa.panda@gmail.com> Date: Thu Jul 17 14:57:10 2025 -0700 fix: use non-dev golang image for operator (#1993) commit 2b29a0a Author: zaristei <zaristei@berkeley.edu> Date: Thu Jul 17 13:10:42 2025 -0700 fix: Working Arm Build Dockerfile for Vllm_v1 (#1844) commit 2430d89 Author: Ryan McCormick <rmccormick@nvidia.com> Date: Thu Jul 17 12:57:46 2025 -0700 test: Add trtllm kv router tests (#1988) commit 1eadc01 Author: Graham King <grahamk@nvidia.com> Date: Thu Jul 17 15:07:41 2025 -0400 feat(runtime): Support tokio-console (#1986) commit b62e633 Author: GuanLuo <41310872+GuanLuo@users.noreply.github.com> Date: Thu Jul 17 11:16:28 2025 -0700 feat: support separate chat_template.jinja file (#1853) commit 8ae3719 Author: Hongkuan Zhou <tedzhouhk@gmail.com> Date: Thu Jul 17 11:12:35 2025 -0700 chore: add some details to dynamo deploy quickstart and fix deploy.sh (#1978) Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com> Co-authored-by: julienmancuso <161955438+julienmancuso@users.noreply.github.com> commit 08891ff Author: Ryan McCormick <rmccormick@nvidia.com> Date: Thu Jul 17 10:57:42 2025 -0700 fix: Update trtllm tests to use new scripts instead of dynamo serve (#1979) commit 49b7a0d Author: Ryan Olson <ryanolson@users.noreply.github.com> Date: Thu Jul 17 08:35:04 2025 -0600 feat: record + analyze logprobs (#1957) commit 6d2be14 Author: Biswa Panda <biswa.panda@gmail.com> Date: Thu Jul 17 00:17:58 2025 -0700 refactor: replace vllm with vllm_v1 container (#1953) Co-authored-by: alec-flowers <aflowers@nvidia.com> commit 4d2a31a Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Wed Jul 16 18:04:09 2025 -0700 chore: add port reservation to utils (#1980) commit 1e3e4a0 Author: Alec <35311602+alec-flowers@users.noreply.github.com> Date: Wed Jul 16 15:54:04 2025 -0700 fix: port race condition through deterministic ports (#1937) commit 4ad281f Author: Tanmay Verma <tanmayv@nvidia.com> Date: Wed Jul 16 14:33:51 2025 -0700 refactor: Move TRTLLM example to the component/backends (#1976) commit 57d24a1 Author: Misha Chornyi <99709299+mc-nv@users.noreply.github.com> Date: Wed Jul 16 14:10:24 2025 -0700 build: Removing shell configuration violations. It's bad practice to hardcod… (#1973) commit 182d3b5 Author: Graham King <grahamk@nvidia.com> Date: Wed Jul 16 16:12:40 2025 -0400 chore(bindings): Remove mistralrs / llama.cpp (#1970) commit def6eaa Author: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com> Date: Wed Jul 16 15:50:23 2025 -0400 feat: attributions for debian deps of sglang, trtllm, vllm runtime containers (#1971) commit f31732a Author: Yan Ru Pei <yanrpei@gmail.com> Date: Wed Jul 16 11:22:15 2025 -0700 feat: integrate mocker with dynamo-run and python cli (#1927) commit aba6099 Author: Graham King <grahamk@nvidia.com> Date: Wed Jul 16 12:26:32 2025 -0400 perf(router): Remove lock from router hot path (#1963) commit b212103 Author: Hongkuan Zhou <tedzhouhk@gmail.com> Date: Wed Jul 16 08:55:33 2025 -0700 docs: add notes in docs to deprecate local connector (#1959) commit 7b325ee Author: Biswa Panda <biswa.panda@gmail.com> Date: Tue Jul 15 18:52:00 2025 -0700 fix: vllm router examples (#1942) commit a50be1a Author: hhzhang16 <54051230+hhzhang16@users.noreply.github.com> Date: Tue Jul 15 17:58:01 2025 -0700 feat: update CODEOWNERS (#1926) commit e260fdf Author: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com> Date: Tue Jul 15 18:49:21 2025 -0400 feat: add bitnami helm chart attribution (#1943) Signed-off-by: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> commit 1c03404 Author: Biswa Panda <biswa.panda@gmail.com> Date: Tue Jul 15 14:26:24 2025 -0700 fix: update inference gateway deployment instructions (#1940) commit 5ca570f Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 16:54:03 2025 -0400 chore: Rename dynamo.ingress to dynamo.frontend (#1944) commit 7b9182f Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 16:33:07 2025 -0400 chore: Move examples/cli to lib/bindings/examples/cli (#1952) commit 40d40dd Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 16:02:19 2025 -0400 chore(multi-modal): Rename frontend.py to web.py (#1951) commit a9e0891 Author: Ryan Olson <ryanolson@users.noreply.github.com> Date: Tue Jul 15 12:30:30 2025 -0600 feat: adding http clients and recorded response stream (#1919) commit 4128d58 Author: Biswa Panda <biswa.panda@gmail.com> Date: Tue Jul 15 10:30:47 2025 -0700 feat: allow helm upgrade using deploy script (#1936) commit 4da078b Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 12:57:38 2025 -0400 fix: Remove OpenSSL dependency, use Rust TLS (#1945) commit fc004d4 Author: jthomson04 <jwillthomson19@gmail.com> Date: Tue Jul 15 08:45:42 2025 -0700 fix: Fix TRT-LLM container build when using a custom pip wheel (#1825) commit 3c6fc6f Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Mon Jul 14 22:35:20 2025 -0700 chore: fix typo (#1938) commit de7fe38 Author: Alec <35311602+alec-flowers@users.noreply.github.com> Date: Mon Jul 14 21:47:12 2025 -0700 feat: add vllm e2e integration tests (#1935) commit 860f3f7 Author: Keiven C <213854356+keivenchang@users.noreply.github.com> Date: Mon Jul 14 21:44:19 2025 -0700 chore: metrics endpoint variables renamed from HTTP_SERVER->SYSTEM (#1934) Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com> commit fc402a3 Author: Biswa Panda <biswa.panda@gmail.com> Date: Mon Jul 14 21:21:20 2025 -0700 feat: configurable namespace for vllm v1 example (#1909) commit df40d2c Author: ZichengMa <zichengma1225@gmail.com> Date: Mon Jul 14 21:11:29 2025 -0700 docs: fix typo and add mount-workspace to vllm doc (#1931) Signed-off-by: ZichengMa <zichengma1225@gmail.com> Co-authored-by: Alec <35311602+alec-flowers@users.noreply.github.com> commit 901715b Author: Tanmay Verma <tanmayv@nvidia.com> Date: Mon Jul 14 20:14:51 2025 -0700 refactor: Refactor the TRTLLM examples remove dynamo SDK (#1884) commit 5bf23d5 Author: hhzhang16 <54051230+hhzhang16@users.noreply.github.com> Date: Mon Jul 14 18:29:19 2025 -0700 feat: update DynamoGraphDeployments for vllm_v1 (#1890) Co-authored-by: mohammedabdulwahhab <furkhan324@berkeley.edu> commit 9e76590 Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Mon Jul 14 17:29:56 2025 -0700 docs: organize sglang readme (#1910) commit ef59ac8 Author: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com> Date: Mon Jul 14 16:16:44 2025 -0700 docs: TRTLLM Example of Llama4+Eagle3 (Speculative Decoding) (#1828) Signed-off-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com> Co-authored-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com> commit 053041e Author: Jorge António <matroid@outlook.com> Date: Tue Jul 15 00:06:38 2025 +0100 fix: resolve incorrect finish reason propagation (#1857) commit 3733f58 Author: Graham King <grahamk@nvidia.com> Date: Mon Jul 14 19:04:22 2025 -0400 feat(backends): Python llama.cpp engine (#1925) commit 6a1350c Author: Tushar Sharma <tusharma@nvidia.com> Date: Mon Jul 14 14:56:36 2025 -0700 build: minor improvements to sglang dockerfile (#1917) commit e2a619b Author: Neelay Shah <neelays@nvidia.com> Date: Mon Jul 14 14:52:53 2025 -0700 fix: remove environment variable passing (#1911) Signed-off-by: Neelay Shah <neelays@nvidia.com> Co-authored-by: Neelay Shah <neelays@a4u8g-0057.ipp2u2.colossus.nvidia.com> commit 3d17a49 Author: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com> Date: Mon Jul 14 14:41:56 2025 -0700 refactor: remove dynamo build (#1778) Signed-off-by: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com> commit 3e0cb07 Author: Anant Sharma <anants@nvidia.com> Date: Mon Jul 14 15:43:48 2025 -0400 fix: copy attributions and license to trtllm runtime container (#1916) commit fc36bf5 Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Mon Jul 14 12:31:49 2025 -0700 feat: receive kvmetrics from sglang scheduler (#1789) Co-authored-by: zixuanzhang226 <zixuanzhang@bytedance.com> commit df91fce Author: Yan Ru Pei <yanrpei@gmail.com> Date: Mon Jul 14 12:24:04 2025 -0700 feat: prefill aware routing (#1895) commit ad8ad66 Author: Graham King <grahamk@nvidia.com> Date: Mon Jul 14 15:20:35 2025 -0400 feat: Shrink the ai-dynamo wheel by 35 MiB (#1918) Remove http and llmctl binaries. They have been unused for a while. commit 480b41d Author: Graham King <grahamk@nvidia.com> Date: Mon Jul 14 15:06:45 2025 -0400 feat: Python frontend / ingress node (#1912)
ZichengMa
added a commit
that referenced
this pull request
Jul 21, 2025
commit d4b5414 Author: atchernych <atchernych@nvidia.com> Date: Mon Jul 21 13:10:24 2025 -0700 fix: mypy error (#2029) commit 79337c7 Author: Ryan McCormick <rmccormick@nvidia.com> Date: Mon Jul 21 12:12:16 2025 -0700 build: support custom TRTLLM build for commits not on main branch (#2021) commit 95dd942 Author: atchernych <atchernych@nvidia.com> Date: Mon Jul 21 12:09:33 2025 -0700 docs: Post-Merge cleanup of the deploy documentation (#1922) commit cb6de94 Author: ptarasiewiczNV <104908264+ptarasiewiczNV@users.noreply.github.com> Date: Sun Jul 20 22:34:50 2025 +0200 chore: Install vLLM and WideEP kernels in vLLM runtime container (#2010) Signed-off-by: Alec <35311602+alec-flowers@users.noreply.github.com> Co-authored-by: Alec <35311602+alec-flowers@users.noreply.github.com> Co-authored-by: alec-flowers <aflowers@nvidia.com> commit fe63c17 Author: Alec <35311602+alec-flowers@users.noreply.github.com> Date: Fri Jul 18 17:45:08 2025 -0700 fix: Revert "feat: add vLLM v1 multi-modal example. Add llama4 Maverick ex… (#2017) commit bf1998f Author: jthomson04 <jwillthomson19@gmail.com> Date: Fri Jul 18 17:23:50 2025 -0700 fix: Don't detokenize twice in TRT-LLM examples (#1955) commit 343a481 Author: Ryan Olson <ryanolson@users.noreply.github.com> Date: Fri Jul 18 16:22:43 2025 -0600 feat: http disconnects (#2014) commit e330d96 Author: Yan Ru Pei <yanrpei@gmail.com> Date: Fri Jul 18 13:40:54 2025 -0700 feat: enable / disable chunked prefill for mockers (#2015) Signed-off-by: Yan Ru Pei <yanrpei@gmail.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> commit 353146e Author: GuanLuo <41310872+GuanLuo@users.noreply.github.com> Date: Fri Jul 18 13:33:36 2025 -0700 feat: add vLLM v1 multi-modal example. Add llama4 Maverick example (#1990) Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com> Co-authored-by: krishung5 <krish@nvidia.com> commit 1f07dab Author: Jacky <18255193+kthui@users.noreply.github.com> Date: Fri Jul 18 13:04:20 2025 -0700 feat: Add migration to LLM requests (#1930) commit 5f17918 Author: Tanmay Verma <tanmayv@nvidia.com> Date: Fri Jul 18 12:59:34 2025 -0700 refactor: Migrate to new UX2 for python launch (#2003) commit fc12436 Author: Graham King <grahamk@nvidia.com> Date: Fri Jul 18 14:52:57 2025 -0400 feat(frontend): router-mode settings (#2001) commit dc75cf1 Author: ptarasiewiczNV <104908264+ptarasiewiczNV@users.noreply.github.com> Date: Fri Jul 18 18:47:28 2025 +0200 chore: Move NIXL repo clone to Dockerfiles (#2009) commit f6f392c Author: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com> Date: Thu Jul 17 18:44:17 2025 -0700 Remove link to the fix for disagg + eagle3 for TRT-LLM example (#2006) Signed-off-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com> commit cc90ca6 Author: atchernych <atchernych@nvidia.com> Date: Thu Jul 17 18:34:40 2025 -0700 feat: Create a convenience script to uninstall Dynamo Deploy CRDs (#1933) commit 267b422 Author: Greg Clark <grclark@nvidia.com> Date: Thu Jul 17 20:44:21 2025 -0400 chore: loosed python requirement versions (#1998) Signed-off-by: Greg Clark <grclark@nvidia.com> commit b8474e5 Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Thu Jul 17 16:35:05 2025 -0700 chore: update cmake and gap installation and sgl in wideep container (#1991) commit 157a3b0 Author: Biswa Panda <biswa.panda@gmail.com> Date: Thu Jul 17 15:38:12 2025 -0700 fix: incorrect helm upgrade command (#2000) commit 0dfca2c Author: Ryan McCormick <rmccormick@nvidia.com> Date: Thu Jul 17 15:33:33 2025 -0700 ci: Update trtllm gitlab triggers for new components directory and test script (#1992) commit f3fb09e Author: Kris Hung <krish@nvidia.com> Date: Thu Jul 17 14:59:59 2025 -0700 fix: Fix syntax for tokio-console (#1997) commit dacffb8 Author: Biswa Panda <biswa.panda@gmail.com> Date: Thu Jul 17 14:57:10 2025 -0700 fix: use non-dev golang image for operator (#1993) commit 2b29a0a Author: zaristei <zaristei@berkeley.edu> Date: Thu Jul 17 13:10:42 2025 -0700 fix: Working Arm Build Dockerfile for Vllm_v1 (#1844) commit 2430d89 Author: Ryan McCormick <rmccormick@nvidia.com> Date: Thu Jul 17 12:57:46 2025 -0700 test: Add trtllm kv router tests (#1988) commit 1eadc01 Author: Graham King <grahamk@nvidia.com> Date: Thu Jul 17 15:07:41 2025 -0400 feat(runtime): Support tokio-console (#1986) commit b62e633 Author: GuanLuo <41310872+GuanLuo@users.noreply.github.com> Date: Thu Jul 17 11:16:28 2025 -0700 feat: support separate chat_template.jinja file (#1853) commit 8ae3719 Author: Hongkuan Zhou <tedzhouhk@gmail.com> Date: Thu Jul 17 11:12:35 2025 -0700 chore: add some details to dynamo deploy quickstart and fix deploy.sh (#1978) Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com> Co-authored-by: julienmancuso <161955438+julienmancuso@users.noreply.github.com> commit 08891ff Author: Ryan McCormick <rmccormick@nvidia.com> Date: Thu Jul 17 10:57:42 2025 -0700 fix: Update trtllm tests to use new scripts instead of dynamo serve (#1979) commit 49b7a0d Author: Ryan Olson <ryanolson@users.noreply.github.com> Date: Thu Jul 17 08:35:04 2025 -0600 feat: record + analyze logprobs (#1957) commit 6d2be14 Author: Biswa Panda <biswa.panda@gmail.com> Date: Thu Jul 17 00:17:58 2025 -0700 refactor: replace vllm with vllm_v1 container (#1953) Co-authored-by: alec-flowers <aflowers@nvidia.com> commit 4d2a31a Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Wed Jul 16 18:04:09 2025 -0700 chore: add port reservation to utils (#1980) commit 1e3e4a0 Author: Alec <35311602+alec-flowers@users.noreply.github.com> Date: Wed Jul 16 15:54:04 2025 -0700 fix: port race condition through deterministic ports (#1937) commit 4ad281f Author: Tanmay Verma <tanmayv@nvidia.com> Date: Wed Jul 16 14:33:51 2025 -0700 refactor: Move TRTLLM example to the component/backends (#1976) commit 57d24a1 Author: Misha Chornyi <99709299+mc-nv@users.noreply.github.com> Date: Wed Jul 16 14:10:24 2025 -0700 build: Removing shell configuration violations. It's bad practice to hardcod… (#1973) commit 182d3b5 Author: Graham King <grahamk@nvidia.com> Date: Wed Jul 16 16:12:40 2025 -0400 chore(bindings): Remove mistralrs / llama.cpp (#1970) commit def6eaa Author: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com> Date: Wed Jul 16 15:50:23 2025 -0400 feat: attributions for debian deps of sglang, trtllm, vllm runtime containers (#1971) commit f31732a Author: Yan Ru Pei <yanrpei@gmail.com> Date: Wed Jul 16 11:22:15 2025 -0700 feat: integrate mocker with dynamo-run and python cli (#1927) commit aba6099 Author: Graham King <grahamk@nvidia.com> Date: Wed Jul 16 12:26:32 2025 -0400 perf(router): Remove lock from router hot path (#1963) commit b212103 Author: Hongkuan Zhou <tedzhouhk@gmail.com> Date: Wed Jul 16 08:55:33 2025 -0700 docs: add notes in docs to deprecate local connector (#1959) commit 7b325ee Author: Biswa Panda <biswa.panda@gmail.com> Date: Tue Jul 15 18:52:00 2025 -0700 fix: vllm router examples (#1942) commit a50be1a Author: hhzhang16 <54051230+hhzhang16@users.noreply.github.com> Date: Tue Jul 15 17:58:01 2025 -0700 feat: update CODEOWNERS (#1926) commit e260fdf Author: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com> Date: Tue Jul 15 18:49:21 2025 -0400 feat: add bitnami helm chart attribution (#1943) Signed-off-by: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> commit 1c03404 Author: Biswa Panda <biswa.panda@gmail.com> Date: Tue Jul 15 14:26:24 2025 -0700 fix: update inference gateway deployment instructions (#1940) commit 5ca570f Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 16:54:03 2025 -0400 chore: Rename dynamo.ingress to dynamo.frontend (#1944) commit 7b9182f Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 16:33:07 2025 -0400 chore: Move examples/cli to lib/bindings/examples/cli (#1952) commit 40d40dd Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 16:02:19 2025 -0400 chore(multi-modal): Rename frontend.py to web.py (#1951) commit a9e0891 Author: Ryan Olson <ryanolson@users.noreply.github.com> Date: Tue Jul 15 12:30:30 2025 -0600 feat: adding http clients and recorded response stream (#1919) commit 4128d58 Author: Biswa Panda <biswa.panda@gmail.com> Date: Tue Jul 15 10:30:47 2025 -0700 feat: allow helm upgrade using deploy script (#1936) commit 4da078b Author: Graham King <grahamk@nvidia.com> Date: Tue Jul 15 12:57:38 2025 -0400 fix: Remove OpenSSL dependency, use Rust TLS (#1945) commit fc004d4 Author: jthomson04 <jwillthomson19@gmail.com> Date: Tue Jul 15 08:45:42 2025 -0700 fix: Fix TRT-LLM container build when using a custom pip wheel (#1825) commit 3c6fc6f Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Mon Jul 14 22:35:20 2025 -0700 chore: fix typo (#1938) commit de7fe38 Author: Alec <35311602+alec-flowers@users.noreply.github.com> Date: Mon Jul 14 21:47:12 2025 -0700 feat: add vllm e2e integration tests (#1935) commit 860f3f7 Author: Keiven C <213854356+keivenchang@users.noreply.github.com> Date: Mon Jul 14 21:44:19 2025 -0700 chore: metrics endpoint variables renamed from HTTP_SERVER->SYSTEM (#1934) Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com> commit fc402a3 Author: Biswa Panda <biswa.panda@gmail.com> Date: Mon Jul 14 21:21:20 2025 -0700 feat: configurable namespace for vllm v1 example (#1909) commit df40d2c Author: ZichengMa <zichengma1225@gmail.com> Date: Mon Jul 14 21:11:29 2025 -0700 docs: fix typo and add mount-workspace to vllm doc (#1931) Signed-off-by: ZichengMa <zichengma1225@gmail.com> Co-authored-by: Alec <35311602+alec-flowers@users.noreply.github.com> commit 901715b Author: Tanmay Verma <tanmayv@nvidia.com> Date: Mon Jul 14 20:14:51 2025 -0700 refactor: Refactor the TRTLLM examples remove dynamo SDK (#1884) commit 5bf23d5 Author: hhzhang16 <54051230+hhzhang16@users.noreply.github.com> Date: Mon Jul 14 18:29:19 2025 -0700 feat: update DynamoGraphDeployments for vllm_v1 (#1890) Co-authored-by: mohammedabdulwahhab <furkhan324@berkeley.edu> commit 9e76590 Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Mon Jul 14 17:29:56 2025 -0700 docs: organize sglang readme (#1910) commit ef59ac8 Author: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com> Date: Mon Jul 14 16:16:44 2025 -0700 docs: TRTLLM Example of Llama4+Eagle3 (Speculative Decoding) (#1828) Signed-off-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com> Co-authored-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com> commit 053041e Author: Jorge António <matroid@outlook.com> Date: Tue Jul 15 00:06:38 2025 +0100 fix: resolve incorrect finish reason propagation (#1857) commit 3733f58 Author: Graham King <grahamk@nvidia.com> Date: Mon Jul 14 19:04:22 2025 -0400 feat(backends): Python llama.cpp engine (#1925) commit 6a1350c Author: Tushar Sharma <tusharma@nvidia.com> Date: Mon Jul 14 14:56:36 2025 -0700 build: minor improvements to sglang dockerfile (#1917) commit e2a619b Author: Neelay Shah <neelays@nvidia.com> Date: Mon Jul 14 14:52:53 2025 -0700 fix: remove environment variable passing (#1911) Signed-off-by: Neelay Shah <neelays@nvidia.com> Co-authored-by: Neelay Shah <neelays@a4u8g-0057.ipp2u2.colossus.nvidia.com> commit 3d17a49 Author: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com> Date: Mon Jul 14 14:41:56 2025 -0700 refactor: remove dynamo build (#1778) Signed-off-by: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com> commit 3e0cb07 Author: Anant Sharma <anants@nvidia.com> Date: Mon Jul 14 15:43:48 2025 -0400 fix: copy attributions and license to trtllm runtime container (#1916) commit fc36bf5 Author: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Date: Mon Jul 14 12:31:49 2025 -0700 feat: receive kvmetrics from sglang scheduler (#1789) Co-authored-by: zixuanzhang226 <zixuanzhang@bytedance.com> commit df91fce Author: Yan Ru Pei <yanrpei@gmail.com> Date: Mon Jul 14 12:24:04 2025 -0700 feat: prefill aware routing (#1895) commit ad8ad66 Author: Graham King <grahamk@nvidia.com> Date: Mon Jul 14 15:20:35 2025 -0400 feat: Shrink the ai-dynamo wheel by 35 MiB (#1918) Remove http and llmctl binaries. They have been unused for a while. commit 480b41d Author: Graham King <grahamk@nvidia.com> Date: Mon Jul 14 15:06:45 2025 -0400 feat: Python frontend / ingress node (#1912)
This was referenced Aug 13, 2025
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
end-to-end test: https://github.com/ai-dynamo/dynamo/blob/ryan/logprob-v2/lib/llm/src/perf/logprobs.rs#L1173
key refactor to async engine and associated traits: 9e63c00
Summary by CodeRabbit
New Features
Refactor
Tests
Chores