[b200] support trt-llm allreduce fuse rms_norm_add kernel #7621
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
There was a problem hiding this comment.
Summary of Changes
Hello @BBuf, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request focuses on optimizing the performance of distributed inference by integrating a fused allreduce and RMS normalization kernel. By leveraging the FlashInfer library, it aims to reduce latency for these common operations, particularly beneficial in multi-GPU environments for large language models.
Highlights
- Performance Optimization: Introduced a new fused kernel for
allreduceandRMSNormoperations, leveraging the FlashInfer library to improve performance in Tensor Parallelism setups, as demonstrated by a reported latency reduction from 13.5us to 8.7us. - FlashInfer Integration: Added a new module (
flashinfer_fusion.py) to manage FlashInfer workspace and expose the fusedallreduce_add_rmsnormfunction, which utilizes FlashInfer'strtllm_allreduce_fusionAPI. - Conditional Execution: Modified the
communicatorandlayernormmodules to conditionally utilize the new fused operation when FlashInfer is available and a multi-GPU environment is detected, falling back to existing implementations otherwise.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
There was a problem hiding this comment.
Code Review
This pull request introduces a performance optimization by leveraging a fused all-reduce and RMS norm kernel from FlashInfer. The changes are well-structured, with a new flashinfer_fusion.py module to handle the integration and workspace management, and modifications in communicator.py and layernorm.py to enable this new path. The implementation looks promising, but a critical correctness issue in the fallback logic and a high-severity issue related to workspace management have been identified. Once these issues are addressed, this will be a great addition to improve performance.
Comment on lines
189
to
190
|
|
||
| return self.forward(x, residual) |
There was a problem hiding this comment.
The fallback logic in forward_with_allreduce_fusion skips the tensor_model_parallel_all_reduce operation when the fused kernel is not available, leading to incorrect results in multi-GPU environments. The all-reduce operation must be performed before applying the layer norm to maintain correctness.
if is_flashinfer_available() and residual is not None:
from sglang.srt.layers.flashinfer_fusion import flashinfer_allreduce_add_rmsnorm
from sglang.srt.distributed import get_tensor_model_parallel_world_size, tensor_model_parallel_all_reduce
# Only use fusion operation in multi-GPU environment
if get_tensor_model_parallel_world_size() > 1:
fused_result = flashinfer_allreduce_add_rmsnorm(
input_tensor=x,
residual=residual,
weight=self.weight,
eps=self.variance_epsilon,
)
if fused_result[0] is not None:
return fused_result
x = tensor_model_parallel_all_reduce(x)
return self.forward(x, residual)
Comment on lines
120
to
122
| if (not _workspace_manager.initialized or | ||
| _workspace_manager.world_size != world_size): | ||
| _workspace_manager.initialize( |
There was a problem hiding this comment.
The condition to check if the workspace needs re-initialization should also include a check for max_token_num and hidden_dim to ensure the workspace is re-initialized if these values change. If these parameters change without re-initialization, it could lead to memory corruption or crashes.
if (not _workspace_manager.initialized or
_workspace_manager.world_size != world_size or
_workspace_manager.max_token_num != max_token_num or
_workspace_manager.hidden_dim != hidden_dim):
Comment on lines
400
to
404
| if hasattr(layernorm, 'forward_with_allreduce_fusion'): | ||
| hidden_states, residual = layernorm.forward_with_allreduce_fusion(hidden_states, residual) | ||
| else: | ||
| hidden_states = tensor_model_parallel_all_reduce(hidden_states) | ||
| hidden_states, residual = layernorm(hidden_states, residual) |
There was a problem hiding this comment.
Consider using getattr with a default value to avoid checking for the attribute forward_with_allreduce_fusion before accessing it. This can simplify the code and make it more readable.
hidden_states, residual = getattr(layernorm, 'forward_with_allreduce_fusion', layernorm)(hidden_states, residual)
Comment on lines
90
to
101
| if self.initialized and self.ipc_handles is not None: | ||
| try: | ||
| _flashinfer_comm.trtllm_destroy_ipc_workspace_for_all_reduce( | ||
| self.ipc_handles, | ||
| group=dist.group.WORLD | ||
| ) | ||
| except Exception as e: | ||
| logger.warning(f"Failed to cleanup FlashInfer workspace: {e}") | ||
| finally: | ||
| self.workspace_tensor = None | ||
| self.ipc_handles = None | ||
| self.initialized = False |
There was a problem hiding this comment.
Consider adding a check to ensure self.initialized is False before attempting to clean up the workspace. This could prevent potential issues if cleanup is called multiple times without a corresponding initialize call.
if self.initialized and self.ipc_handles is not None:
if not self.initialized:
return
try:
ispobock
reviewed
Jun 28, 2025
ispobock
approved these changes
Jun 30, 2025
|
Refer to trt-llm , I change sglang python3 test/srt/parse_results.py dsv3_main.jsonl
Saved summary to: dsv3_main_summary.csv
+----+-------------------+--------------------+---------------------+----------------+------------------+---------------+----------------+------------------+---------------+-----------------------+
| | max_concurrency | input_throughput | output_throughput | mean_ttft_ms | median_ttft_ms | p99_ttft_ms | mean_tpot_ms | median_tpot_ms | p99_tpot_ms | per_user_throughput |
+====+===================+====================+=====================+================+==================+===============+================+==================+===============+=======================+
| 0 | 1.000 | 133.166 | 133.166 | 176.653 | 153.561 | 226.394 | 7.337 | 7.599 | 8.060 | 133.166 |
+----+-------------------+--------------------+---------------------+----------------+------------------+---------------+----------------+------------------+---------------+-----------------------+
| 1 | 4.000 | 390.269 | 390.269 | 254.178 | 207.857 | 646.446 | 9.880 | 9.689 | 11.796 | 97.567 |
+----+-------------------+--------------------+---------------------+----------------+------------------+---------------+----------------+------------------+---------------+-----------------------+
| 2 | 16.000 | 1018.889 | 1018.889 | 275.613 | 179.920 | 643.978 | 14.551 | 14.247 | 20.015 | 63.681 |
+----+-------------------+--------------------+---------------------+----------------+------------------+---------------+----------------+------------------+---------------+-----------------------+
➜ sglang python3 test/srt/parse_results.py dsv3_pr.jsonl
Saved summary to: dsv3_pr_summary.csv
+----+-------------------+--------------------+---------------------+----------------+------------------+---------------+----------------+------------------+---------------+-----------------------+
| | max_concurrency | input_throughput | output_throughput | mean_ttft_ms | median_ttft_ms | p99_ttft_ms | mean_tpot_ms | median_tpot_ms | p99_tpot_ms | per_user_throughput |
+====+===================+====================+=====================+================+==================+===============+================+==================+===============+=======================+
| 0 | 1.000 | 137.713 | 137.713 | 167.537 | 153.134 | 219.778 | 7.098 | 6.992 | 7.747 | 137.713 |
+----+-------------------+--------------------+---------------------+----------------+------------------+---------------+----------------+------------------+---------------+-----------------------+
| 1 | 4.000 | 409.847 | 409.847 | 208.332 | 156.417 | 537.090 | 9.388 | 9.090 | 11.284 | 102.462 |
+----+-------------------+--------------------+---------------------+----------------+------------------+---------------+----------------+------------------+---------------+-----------------------+
| 2 | 16.000 | 1055.758 | 1055.758 | 269.626 | 164.852 | 643.074 | 13.910 | 13.589 | 18.392 | 65.985 |
+----+-------------------+--------------------+---------------------+----------------+------------------+---------------+----------------+------------------+---------------+-----------------------+bs=1, 3.4%+ |
Alcanderian
reviewed
Jun 30, 2025
| and is_flashinfer_available() | ||
| and hasattr(layernorm, "forward_with_allreduce_fusion") | ||
| and global_server_args_dict["enable_flashinfer_allreduce_fusion"] | ||
| and hidden_states.shape[0] <= 1024 |
There was a problem hiding this comment.
hidden_state.numel() * hidden_state.element_size() < THRESHOLD
There was a problem hiding this comment.
Make sense, I'll update it.
There was a problem hiding this comment.
I think this feature could also be applied to other models. However, since different models may have varying hidden_size values, directly checking max_token_num seems more general. Regarding the token number 1024: This value was estimated based on the workspace threshold in trt_llm, using ds-v3's hidden_size as a reference. With 1024 tokens, it only allocates an additional ~10MB buffer, so the memory overhead is minimal.
There was a problem hiding this comment.
Hi,
I think the max_workspace settings in trt-llm are not for these flashinfer kernels (allreduce_fusion_xxx).
The max_token_number should be set as the actual max token number.
The default value of use_oneshot should be False. In these two cases it could be set as True. (https://github.com/NVIDIA/TensorRT-LLM/blob/a1235ee9781050e562bbce2c86f714c38d434dbe/cpp/tensorrt_llm/thop/allreduceOp.cpp#L416-L429)
5 tasks
yzh119
pushed a commit
to flashinfer-ai/flashinfer
that referenced
this pull request
Jun 30, 2025
<!-- .github/pull_request_template.md --> ## 📌 Description ref sgl-project/sglang#7621 <!-- What does this PR do? Briefly describe the changes and why they’re needed. --> ## 🔍 Related Issues <!-- Link any related issues here --> ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [x] All tests are passing (`unittest`, etc.). ## Reviewer Notes <!-- Optional: anything you'd like reviewers to focus on, concerns, etc. -->
…-project/sglang into support_allreduce_rmsnorm_add_fusion
zhyncs
requested changes
Jul 2, 2025
zhyncs
reviewed
Jul 2, 2025
zhyncs
approved these changes
Jul 3, 2025
Merged
5 tasks
yzh119
pushed a commit
to flashinfer-ai/flashinfer
that referenced
this pull request
Jul 8, 2025
<!-- .github/pull_request_template.md --> ## 📌 Description <!-- What does this PR do? Briefly describe the changes and why they’re needed. --> We add some notes on each api to help integration to vllm/sgl. And we try to fix the error in issues. To avoid workspace size overflow, the max lamport communication size MAX_COMM_SIZE (computed as hidden * max_token) should be less than round_down(INT_32_MAX, 2MB). For any larger size, it would be rewritten to this value with a warning "warning: lamport_comm_size 2147483648 is greater than MAX_COMM_SIZE 2145386496, set to MAX_COMM_SIZE". If the actual lamport communication size (computed as hidden * token_num) exceeds this MAX_COMM_SIZE, always set use_oneshot to be False. Otherwise, you could set use_oneshot on your preference; and for the min-latency case, set it to be (token_num <= 128). ## 🔍 Related Issues #1223 sgl-project/sglang#7621 ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [x] All tests are passing (`unittest`, etc.). ## Reviewer Notes <!-- Optional: anything you'd like reviewers to focus on, concerns, etc. --> --------- Co-authored-by: averyh <averyh@nvidia.com>
chenxijun1029
pushed a commit
to chenxijun1029/sglang
that referenced
this pull request
Jul 17, 2025
pi314ever
pushed a commit
to pi314ever/sglang
that referenced
this pull request
Jul 17, 2025
* Use seq_len_fill_value in the cuda graph runners (sgl-project#7233) * support custom weight loader for model runner (sgl-project#7122) Co-authored-by: kavioyu <kavioyu@tencent.com> * Fix AMD speculative decoding (sgl-project#7252) * [Refactor] OAI Server components (sgl-project#7167) Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> * OAI Server Skeleton & Core Utility Endpoints (sgl-project#7179) * [amd] Opt dsv3 moe (sgl-project#7160) Co-authored-by: wunhuang <wunhuang@amd.com> * update ci node for xeon (sgl-project#7265) * feat: mtp support dp-attention (sgl-project#6081) Co-authored-by: austindeng <austindeng@tencent.com> Co-authored-by: tianqilin.99 <tianqilin.99@bytedance.com> Co-authored-by: Qiaolin Yu <liin1211@outlook.com> Co-authored-by: ch-wan <cwan39@gatech.edu> * support qwen2 running on ascend npu device (sgl-project#7022) Co-authored-by: 刁莹煜 <diaoyingyu1@hisilicon.com> * Fix Deepseek R1 0528 FP4 tensor name mismatch issue during weights loading. (sgl-project#7164) * bugfix(tool call ebnf): Fix EBNF generation for optional function parameters (sgl-project#7283) * Fix AWQ Dequant and Weight Loading of deepseek v2 (sgl-project#6842) * fix: resolve b200 dsv3 mtp issue (sgl-project#7286) * ci: Fix test_ebnf_generate_all_optional_function_params (sgl-project#7288) * fix: only enable flash_attn test on sm80 sm90 (sgl-project#7289) * [PD] Support get local ip from NIC for PD disaggregation (sgl-project#7237) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> * [PD] Add custom memory pool option to support Mooncake PD with NVLink (sgl-project#7264) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> * Upstreaming hicache bug fixes (sgl-project#7267) * Update python API of activation, topk, norm and rope and remove vllm dependency (sgl-project#6614) Co-authored-by: Wu, Chunyuan <chunyuan.wu@intel.com> Co-authored-by: jianan-gu <jianan.gu@intel.com> Co-authored-by: sdp <sdp@gnr799219.jf.intel.com> * Fix hicache benchmark script bug - some sampled input_request is [] (sgl-project#7300) * chore: change logs from`INFO` to `DEBUG` for dp and add force quit for tokenizer manager (sgl-project#7251) * update invalid link in doc (sgl-project#7297) * Fix mini_lb for PD with long output: limit chunk size of decode response (sgl-project#7301) Signed-off-by: ch-tiger1 <xyz@ch-tech.ip-ddns.com> Co-authored-by: ch-tiger1 <xyz@ch-tech.ip-ddns.com> * Fix profiler error when there are idle passes (sgl-project#7003) * [pd] optimize dockerfile for pd disaggregation (sgl-project#7319) Co-authored-by: zhyncs <me@zhyncs.com> * Merge PDLB (Prefill-Decode Load Balancer) into SGLang Router (sgl-project#7096) * Add more refactored openai test & in CI (sgl-project#7284) * fix: resolve blackwell deepep image issue (sgl-project#7331) * add seed in CPU UTs to avoid flaky failure (sgl-project#7333) * Multi-Stage Awake: Support Resume and Pause KV Cache and Weights separately (sgl-project#7099) * Reintroduce tiny fix sampler error when prob is not contiguous (sgl-project#7354) * [Refactor] Clean up radix cache related API (sgl-project#7303) Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu> * Put `_normalize_rid` before other normalization in `io_struct` (sgl-project#7363) * [PD] Transfer hidden states for mtp when disaggregation (sgl-project#7242) * [Bugfix][PD] Set conclude state before clear when failure happens (sgl-project#7362) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> * docs: update installation (sgl-project#7366) * [Docker] optimize dockerfile remove deepep and blackwell merge it to… (sgl-project#7343) Co-authored-by: Yineng Zhang <me@zhyncs.com> * Clean unused import for mimo mtp model (sgl-project#7370) * [Bugfix]Fix hang bug using dp attention with HiRadixCache (sgl-project#7159) Signed-off-by: huanglong <huanglong@linux.alibaba.com> * [Doc] add embedding rerank doc (sgl-project#7364) * Fix judgment condition for enabling Deepseek V3/R1 shared expert fusion optimization (sgl-project#7371) * Feat/refactor embedding server (sgl-project#7322) * Purge VerlEngine (sgl-project#7326) Signed-off-by: Ata Fatahi <immrata@gmail.com> * support return logprobs for pipeline (sgl-project#7356) Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com> * [PD] Optimize custom mem pool usage and bump mooncake version (sgl-project#7393) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> * Support THUDM/GLM-4-0414 (GLM-Z1) Glm4ForCausalLM architecture. (sgl-project#5485) * Refine OpenAI serving entrypoint to remove batch requests (sgl-project#7372) Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> Co-authored-by: Chang Su <csu272@usc.edu> * [Feature] Comprehensive Hybrid Parallelism Support (sgl-project#6389) * [DeepSeekNextN] fix: residual of head norm can be None (sgl-project#7398) * [OAI refactor] Add rerank and score serving (sgl-project#7399) Co-authored-by: Chang Su <chang.s.su@oracle.com> * [OAI Server Refactor] [ChatCompletions & Completions] Implement UsageInfo Processor (sgl-project#7360) Co-authored-by: Chang Su <chang.s.su@oracle.com> * Fix All-Gather under world size one (sgl-project#7219) * Optimize DP attn scheduling for speculative decoding (sgl-project#7285) * Update usage_processor.py (sgl-project#7402) * Fix 7285 Merge Conflicts (sgl-project#7403) * chore: upgrade mooncake-transfer-engine 0.3.4 (sgl-project#7401) * [OAI Server Refactor] [ChatCompletions & Completions] Support Return Hidden State (sgl-project#7329) Signed-off-by: keru <rukeyang@gmail.com> * Remove batches api in docs & example (sgl-project#7400) * [BugFix]: fix EmbeddingReqInput single input error (sgl-project#7396) * [BugFix]fix qwen25 invoke function call streaming responses with curly braces as the starting indicator (sgl-project#7394) * fix overlap pagecount (sgl-project#6984) Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu> * fix: Fix CI test_function_call_parser.py (sgl-project#7425) * Fix CPU offloading for MLA memory pool (sgl-project#7409) * [fix] PD disaggregation when enable mtp and tp!=dp (sgl-project#7420) * feat(oai refactor): Replace `openai_api` with `entrypoints/openai` (sgl-project#7351) Co-authored-by: Jin Pan <jpan236@wisc.edu> * Refactor LoRAManager and LoRAMemoryPool state management logic for dynamic LoRA loading support (sgl-project#7412) * refactor(test): reorganize OpenAI test file structure (sgl-project#7408) * [minor] simplify the `TokenToKVPoolAllocator` (sgl-project#7414) * Tiny add logging for GC (sgl-project#7406) * FlashInfer NVFP4 MoE with EP & 2-stream shared expert (sgl-project#7327) Co-authored-by: JieXin Liang <Alcanderian@users.noreply.github.com> Co-authored-by: alcanderian <alcanderian@gmail.com> * Remove copy after bmm (sgl-project#7441) * Fix torch compile run (sgl-project#7391) Co-authored-by: wunhuang <wunhuang@amd.com> Co-authored-by: Sai Enduri <saimanas.enduri@amd.com> * [misc] Add PD service discovery support in router (sgl-project#7361) * add fused moe config for qwen3 in triton3.3.1 (sgl-project#7445) * Fix CUDA Graph Check under Deepep with DP FFN (sgl-project#7451) * Update hyperparameter_tuning.md (sgl-project#7454) * feat: integrate deepgemm into EPMoE (sgl-project#6821) Co-authored-by: tianqilin.99 <tianqilin.99@bytedance.com> Co-authored-by: TianQiLin666666 <1834987979@qq.com> Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com> * Solve docker build failed in the virtual machine (sgl-project#7290) Co-authored-by: wunhuang <wunhuang@amd.com> Co-authored-by: Sai Enduri <saimanas.enduri@amd.com> Co-authored-by: HAI <hixiao@gmail.com> * Fix a bug in BatchTokenIDOut & Misc style and dependency updates (sgl-project#7457) * [CI] Upgrade mooncake to 0.3.4.post1 to fix 8 gpu tests (sgl-project#7472) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> * Fix prefill OOM due to wrong token calculation when page > 1 (sgl-project#7397) * feat(func_call): Add more check in `BaseFormatDetector.parse_streaming_increment` (sgl-project#7479) * Fix dtype for idle input in spec decoding (sgl-project#7456) * update mooncake in dockerfile (sgl-project#7480) * kvcache io kernels and test case (sgl-project#7382) * [perf] slightly imporve DeepSeek-R1-FP4 TP8 (sgl-project#7481) * Quick fix for DeepGemm requant to also cover MTP. (sgl-project#7378) * Support weight loading without mmap (sgl-project#7469) * ci: Revert openai_server related tests in AMD suites (sgl-project#7449) * Perormance: Enable cuda graph for dp idle batch (sgl-project#7269) Co-authored-by: austindeng <austindeng@tencent.com> Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com> Co-authored-by: ch-wan <cwan39@gatech.edu> * bugfix: Prevent global mutation of conv.stop_str across requests (sgl-project#7347) Co-authored-by: Chang Su <chang.s.su@oracle.com> * Fix RequestValidationError response format (sgl-project#7487) * Fix MTP with Deepseek R1 Fp4 (sgl-project#7376) * chore: bump sgl-kernel v0.2.0 (sgl-project#7490) * chore: bump v0.4.8 (sgl-project#7493) * [AMD] add aiter fused moe in DeepEP path (sgl-project#7268) * enable aiter_biased_grouped_topk kernel (sgl-project#7423) * [PD Disaggregation] replace transfer with batch transfer for better performance (sgl-project#7236) * Remove cumsum_buffer initilization (sgl-project#7439) * [benchmark] fbgemm benchmark support bandwidth report and support fbgemm_cutlass_gmm (sgl-project#7422) * Support multi-thread model weight loading (sgl-project#7277) * [PD] NIXL: Register kv args in advance and cleanup finished requests (sgl-project#6717) * fix: Add `--model` as an alias for `--model-path` in server_args (sgl-project#7505) * misc: Improvement to serving_chat.py and add more ut (sgl-project#7489) * Fuse sorted_token_ids padding to moe_align_block_size kernel (sgl-project#7437) * [OAI] patch origin request_id logic (sgl-project#7508) * [PD][Spec] Fix hidden state transfer for spec decode (sgl-project#7516) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> * EPLB support for MTP (sgl-project#7510) * clean duplicate code (sgl-project#7512) * [ci] add router benchmark script and CI (sgl-project#7498) * fix: force synchronization between TP workers when update_weights (sgl-project#6626) Co-authored-by: dangkai.dk <dangkai.dk@alibaba-inc.com> * [CPU] [BF16] Call fused_experts_cpu, weight_packed_linear and bmm_cpu kernel in DeepSeek model (sgl-project#6641) Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg> * [CI] Upgrade mooncake to v0.3.4.post2 to fix potential slice failed bug (sgl-project#7522) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> * npu fused op (sgl-project#7386) Co-authored-by: Li Junwen <lijunwen13@hisilicon.com> * feat: send kvmetrics from sglang scheduler (sgl-project#6721) * [PD] Add different TP sizes support for no-MLA models (sgl-project#6793) Co-authored-by: shangmingc <csmthu@gmail.com> Co-authored-by: Shangming Cai <caishangming@linux.alibaba.com> * enable aiter fp8 blockscale quant (sgl-project#7520) * take aiter get_rope back (sgl-project#7521) * Fix typo of flash_cache (sgl-project#7513) * feat: add return hidden_states at async generation (sgl-project#7507) * minor: 'role' must be system/assistant/tool, but case insensitive for now (sgl-project#7499) * Fix FP8 KV Cache Support in FA3 Backend (sgl-project#7148) * Fix gathered_buffer issues in tbo (sgl-project#7531) * [PD] Raise error for incompatible mooncake version and some minor fixes (sgl-project#7527) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> * [CMake] Fix sgl-kernel CMakeLists for Blackwell (sgl-project#7543) * Add Tencent HunYuanMoEV1 model support (sgl-project#7549) * Update seed in CPU UTs to avoid flaky failure with single test (sgl-project#7544) * chore: improve ci bug reporting (sgl-project#7542) * chore: remove vlm unnecessary import (sgl-project#7541) Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> Co-authored-by: yhyang201 <yhyang201@gmail.com> Co-authored-by: Mick <mickjagger19@icloud.com> * chore: bump v0.4.8.post1 (sgl-project#7559) * [PD][NIXL] Set is_sorted=False to fix NIXL_ERR_NOT_FOUND (sgl-project#7330) * [Fix] incorrect assert in EPLB (sgl-project#7575) * Updates Gemma3n MLP layer to adapt latest transformers version (sgl-project#7573) Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> * Fix MTP error when enabling two-batch overlap (sgl-project#7569) * Add e2e test for multi instance multi stage memory release/resume occupuation (sgl-project#7208) Signed-off-by: Ata Fatahi <immrata@gmail.com> * [CI] Add CI Testing for Prefill-Decode Disaggregation with Router (sgl-project#7540) * Updates transformers and timm dependencies (sgl-project#7577) Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> * feat: support compatibility between MTP and two-batch-overlap (sgl-project#7225) Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com> * Move multimodal processors into a separate folder (sgl-project#7581) * Fix broken CI TestVILAServer (sgl-project#7610) * [router] add centralized configuration module for sgl-router (sgl-project#7588) * Fix: Minicpm (sgl-project#7612) Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> * Hybrid kv cache for LLaMA4 (sgl-project#6563) Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com> Co-authored-by: tarinkk <rt572@physics.rutger.edu> Co-authored-by: tarinkk <rt572@rutgers.physics.edu> Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com> * [CPU] add optimizations for INT8 and FP8 DeepSeek (sgl-project#6769) Co-authored-by: Zheng, Beilei <beilei.zheng@intel.com> * Tiny add logs for expert location updater (sgl-project#7308) * Fix flakiness in LoRA batch test. (sgl-project#7552) * [BUG] fix local_rank in initialize_dp_attention (sgl-project#7584) * Support dynamic LoRA loading / unloading in engine/server API (sgl-project#7446) * [PD] Respect sampling_params.max_new_tokens when PD disaggregation is activated (sgl-project#7598) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> * fix unit tests (sgl-project#7618) * Let ep_scatter support arbitrary strides / ue8m0 format (sgl-project#7309) * Let EP prefill support new DeepGEMM (sgl-project#7310) * docs: add gb200 nvl72 and a16z grant (sgl-project#7620) * oai: Adds support for OpenAI chat completions API in bench_serving (sgl-project#7036) Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> Co-authored-by: yhyang201 <47235274+yhyang201@users.noreply.github.com> Co-authored-by: Mick <mickjagger19@icloud.com> * [bugfix] Remove PR comment posting from Rust benchmark workflow (sgl-project#7625) * [Minor] clean up multimodal processor and tokenizer manager (sgl-project#7624) * Add dsv3 fused a gemm to sgl-kernel (sgl-project#7630) * Add @mickqian as the CODEOWNERS of multimodal (sgl-project#7636) * Fix stream reasoning parser and Adds Kimi reasoning parser (sgl-project#7432) Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> * Fix sgl-router startup crash (sgl-project#7619) * [bugfix] fix runtime dropping panic in editable (sgl-project#7628) * Move files related to EPLB (sgl-project#7580) * [misc] reduce weird rope_scaling_factor warning (sgl-project#7176) * [AMD] Add unit-test-sgl-kernel-amd to AMD CI (sgl-project#7539) * Update CODEOWNERS (sgl-project#7640) * [EAGLE] remove a wrong adjustment for page_size > 1 & topk > 1 in server_args.py (sgl-project#7643) * [CPU] add c++ kernel to bind CPU cores and memory node (sgl-project#7524) * Improve streaming, log_level, memory report, weight loading, and benchmark script (sgl-project#7632) Co-authored-by: Kan Wu <wukanustc@gmail.com> * Add dsv3 router gemm kernel (sgl-project#7627) * chore: upgrade flashinfer v0.2.7 jit (sgl-project#7663) * [doc] update lws doc for pd (sgl-project#7318) * Fix: sync prepare_fp8_layer_for_marlin with latest vllm changes (sgl-project#7648) * Add small requirements for benchmark/parse_result tools (sgl-project#7671) * [CPU] remove process_group from inputs of shm_allreduce and shm_allgather (sgl-project#7486) * chore: bump sgl-kernel v0.2.1 (sgl-project#7675) * support llama4 eagle3 (sgl-project#6985) Co-authored-by: shuaills <shishuaiuoe@gmail.com> Co-authored-by: Shenggui Li <somerlee.9@gmail.com> Co-authored-by: Yingyi Huang <yingyihuang2000@outlook.com> Co-authored-by: yizhang2077 <1109276519@qq.com> * Refactor mm processors and Enable mixed modality processing (sgl-project#7629) Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> * upgrade sgl kernel to 0.2.1 for main (sgl-project#7676) * add description for llama4 eagle3 (sgl-project#7688) * fix(model loader): use safe_open to prevent file handle leaks. (sgl-project#7684) * chore: upgrade flashinfer v0.2.7.post1 (sgl-project#7698) * Improve error handling for requests with unloaded LoRA path(s) (sgl-project#7642) * Apply dsv3_fused_a_gemm kernel (sgl-project#7635) * Fix GPTQMarlinMoE (sgl-project#7697) * [1/n] apply wna16marlin kernel in moe weight only quantization (sgl-project#7683) Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com> Co-authored-by: yych0745 <1398089567@qq.com> Co-authored-by: HandH1998 <1335248067@qq.com> Co-authored-by: 弋云 <yiyun.wyt@antgroup.com> Co-authored-by: walker-ai <2398833647@qq.com> * Apply dsv3 router gemm kernel for deepseek-r1 fp4 (sgl-project#7677) * [AMD] Temporarily disable test_no_overlap_scheduler and test_vision_chunked_prefill (sgl-project#7717) * [RL] add --skip-warmup (sgl-project#7416) * [RL] support update_weights_from_distributed with different group and multiple weights (sgl-project#7292) * [router] add --log-level to sgl-router (sgl-project#6512) * [b200] support trt-llm allreduce fuse rms_norm_add kernel (sgl-project#7621) * [CPU] Bind threads and numa node for each TP rank (sgl-project#6549) Co-authored-by: srinarayan-srikanthan <srinarayan.srikanthan@intel.com> * Support non-contiguous query input for extend/decode attention (sgl-project#7462) * Support updating weights at once by stopping all requests (sgl-project#6698) Signed-off-by: Tianyu Zhou <albert.zty@antgroup.com> Co-authored-by: Zilin Zhu <zhuzilinallen@gmail.com> * Fix num_tokens_pre_allocated in disaggregation log (sgl-project#7714) * [CPU] [sgl-kernel] set dispatch key of initialize to CatchAll (sgl-project#7734) * [CPU] fix all_reduce and all_gather (sgl-project#6770) Co-authored-by: blzheng <beilei.zheng@intel.com> * fix awq and dsv3 fused gemm compatible (sgl-project#7735) * [CI][Router] Fix bench_one_batch_server for pd router test (sgl-project#7731) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> * Add CUTLASS FP8 Blockscale MoE kernel for Hopper architecture (sgl-project#7278) Co-authored-by: HydraQYH <QYH820@Outlook.com> Co-authored-by: TianQiLin666666 <1834987979@qq.com> * fix dsv3 fused proj check (sgl-project#7738) * Ascend attention backend(PA&MLA) (sgl-project#7722) Co-authored-by: Maksim <makcum888e@mail.ru> Co-authored-by: VDV1985 <vladdv85@mail.ru> * [fix] fix dsv3_router_gemm filter (sgl-project#7750) * [CPU] refine CPU integration code (sgl-project#7647) * [CPU] support the case where num_attention_heads or intermediate_size is not divisible by the TP size (sgl-project#6771) * support qwen3 dense model dp attention (sgl-project#7681) * [optimize] add two stream norm for qwen3 (sgl-project#7740) Co-authored-by: ispobock <ispobaoke@gmail.com> * feat: use D2D instead of H2H in pp (sgl-project#7673) Co-authored-by: alpha-baby <fujianhao1997@qq.com> * [Bug] add flashinfer bool check for fusedmoe in Qwen moe models (sgl-project#7723) * [fix] put cpu in the first priority in get_device() (sgl-project#7752) * [optimize] fuse renormalize into moe_topk_softmax (sgl-project#7744) Co-authored-by: ispobock <ispobaoke@gmail.com> * chore: bump sgl-kernel 0.2.2 (sgl-project#7755) * fix CI: update native api ipynb (sgl-project#7754) Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> * fuse renormal into moe topk softmax kernel python code (sgl-project#7751) Co-authored-by: ispobock <ispobaoke@gmail.com> Co-authored-by: zhyncs <me@zhyncs.com> * Remove type conversion and fix id map in topk (sgl-project#7759) * Add V2-lite model test (sgl-project#7390) Co-authored-by: DiweiSun <105627594+DiweiSun@users.noreply.github.com> * refactor llama4 dp attention logic (sgl-project#7729) * fix(docs): fix the broken link in `docs/references/production_metrics.md` (sgl-project#7741) Signed-off-by: rudeigerc <rudeigerc@gmail.com> * [fix] update bench_speculative.py for compatibility (sgl-project#7764) Signed-off-by: Kay Yan <kay.yan@daocloud.io> * Move mem_fraction_static adjustment for multimodal models to `server_args.py` & Fix session control & Other cleanups (sgl-project#7748) * [RL] Add --nccl-port to prevent port conflict (sgl-project#7418) * [RL] add pause and continue generation for async rl training (sgl-project#7419) * [Fix] Alloc return type error (sgl-project#7778) Signed-off-by: Capronir <839972205@qq.com> * [feat] Support EAGLE3 for Qwen (sgl-project#7745) Co-authored-by: 纬杭 <ximing.wxm@antgroup.com> Co-authored-by: zyksir <zyksir@outlook.com> * saving hidden_states.clone() (sgl-project#7705) * [1/n]: add cutlass W4A8 moe kernel for hopper architecture (sgl-project#7772) Signed-off-by: yangsijia.614 <yangsijia.614@bytedance.com> Co-authored-by: yicwang <yichen.wang@bytedance.com> * add model: qwen2-audio (sgl-project#7596) * Optimize Hopper CUTLASS FP8 Blockwise Grouped GEMM Kernel in Small K Scenario (sgl-project#7782) * Embedding parallel by attn_tp (sgl-project#7623) * fix: fix apply_shuffle_mul_sum (sgl-project#7444) * chore: bump sgl-kernel v0.2.3 (sgl-project#7784) * fix: use nvidia-nccl-cu12 2.27.5 (sgl-project#7787) * DP Attention with Auto DeepEP Dispatch (sgl-project#7222) * chore: upgrade sgl-kernel v0.2.3 (sgl-project#7786) * Fix incorrect spec_num_draft_tokens in draft_extend (sgl-project#7757) * [fix] fix misusing of is_cuda (sgl-project#7790) * Add treemask mode to build_eagle_tree & release sgl-kernel 0.2.3 (sgl-project#7756) Co-authored-by: Pranjal Shankhdhar <pranjal.ssh@gmail.com> * chore: bump sgl-kernel v0.2.4 (sgl-project#7800) * ci: fix port args (sgl-project#7792) * Fix CI test OOM issue. (sgl-project#7799) * chore: upgrade sgl-kernel v0.2.4 (sgl-project#7801) * chore: bump v0.4.9 (sgl-project#7802) * fix merge conflict issue * fix hpu attention nonetyep issue * fix alignment * fix alignment2 * Ci failure fixes * fix attention-backend choices --------- Signed-off-by: Xinyuan Tong <justinning0323@outlook.com> Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> Signed-off-by: ch-tiger1 <xyz@ch-tech.ip-ddns.com> Signed-off-by: huanglong <huanglong@linux.alibaba.com> Signed-off-by: Ata Fatahi <immrata@gmail.com> Signed-off-by: keru <rukeyang@gmail.com> Signed-off-by: Tianyu Zhou <albert.zty@antgroup.com> Signed-off-by: rudeigerc <rudeigerc@gmail.com> Signed-off-by: Kay Yan <kay.yan@daocloud.io> Signed-off-by: Capronir <839972205@qq.com> Signed-off-by: yangsijia.614 <yangsijia.614@bytedance.com> Signed-off-by: Mohit Sinha <msinha@habana.ai> Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com> Co-authored-by: KavioYu <67678385+yukavio@users.noreply.github.com> Co-authored-by: kavioyu <kavioyu@tencent.com> Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com> Co-authored-by: yhyang201 <47235274+yhyang201@users.noreply.github.com> Co-authored-by: kk <43161300+kkHuang-amd@users.noreply.github.com> Co-authored-by: wunhuang <wunhuang@amd.com> Co-authored-by: DiweiSun <105627594+DiweiSun@users.noreply.github.com> Co-authored-by: u4lr451 <u4lr451@gmail.com> Co-authored-by: austindeng <austindeng@tencent.com> Co-authored-by: tianqilin.99 <tianqilin.99@bytedance.com> Co-authored-by: Qiaolin Yu <liin1211@outlook.com> Co-authored-by: ch-wan <cwan39@gatech.edu> Co-authored-by: Yijie Zhu <762412795@qq.com> Co-authored-by: 刁莹煜 <diaoyingyu1@hisilicon.com> Co-authored-by: Charles Chen <pychen96@gmail.com> Co-authored-by: Chang Su <chang.s.su@oracle.com> Co-authored-by: AniZpZ <zhuangsen.zp@antgroup.com> Co-authored-by: Yineng Zhang <me@zhyncs.com> Co-authored-by: shangmingc <caishangming@linux.alibaba.com> Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu> Co-authored-by: YanbingJiang <yanbing.jiang@intel.com> Co-authored-by: Wu, Chunyuan <chunyuan.wu@intel.com> Co-authored-by: jianan-gu <jianan.gu@intel.com> Co-authored-by: sdp <sdp@gnr799219.jf.intel.com> Co-authored-by: Binyao Jiang <byjiang1996@gmail.com> Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com> Co-authored-by: linzhuo <15313137931lz@gmail.com> Co-authored-by: ch-tiger1 <tiger@ch-tech.ip-ddns.com> Co-authored-by: ch-tiger1 <xyz@ch-tech.ip-ddns.com> Co-authored-by: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com> Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com> Co-authored-by: Simo Lin <linsimo.mark@gmail.com> Co-authored-by: Jinn <47354855+jhinpan@users.noreply.github.com> Co-authored-by: Stefan He <hebiaobuaa@gmail.com> Co-authored-by: DarkSharpness <76582120+DarkSharpness@users.noreply.github.com> Co-authored-by: Atream <80757050+Atream@users.noreply.github.com> Co-authored-by: Li Hui <lambert80.ios@gmail.com> Co-authored-by: Huang Long <121648372+LLLL114@users.noreply.github.com> Co-authored-by: woodx <124784234+woodx9@users.noreply.github.com> Co-authored-by: Ata Fatahi <immrata@gmail.com> Co-authored-by: strgrb <zhangkaihong.zkh@antgroup.com> Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com> Co-authored-by: Wenbo Yang <solrex@users.noreply.github.com> Co-authored-by: Chang Su <csu272@usc.edu> Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com> Co-authored-by: Keyang Ru <rukeyang@gmail.com> Co-authored-by: ehuaa <ehuamail@163.com> Co-authored-by: pansicheng <sicheng.pan.chn@gmail.com> Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com> Co-authored-by: Jin Pan <jpan236@wisc.edu> Co-authored-by: Lifu Huang <lifu.hlf@gmail.com> Co-authored-by: Trevor Morris <tmorris@nvidia.com> Co-authored-by: JieXin Liang <Alcanderian@users.noreply.github.com> Co-authored-by: alcanderian <alcanderian@gmail.com> Co-authored-by: Ke Bao <ISPObaoke@163.com> Co-authored-by: Sai Enduri <saimanas.enduri@amd.com> Co-authored-by: Yi Zhang <1109276519@qq.com> Co-authored-by: xutizhou <xutingz@nvidia.com> Co-authored-by: TianQiLin666666 <1834987979@qq.com> Co-authored-by: HAI <hixiao@gmail.com> Co-authored-by: Yuhong Guo <guoyuhong1985@outlook.com> Co-authored-by: huangtingwei <141888744+huangtingwei9988@users.noreply.github.com> Co-authored-by: Alex Sun <alex.s@amd.com> Co-authored-by: valarLip <103567126+valarLip@users.noreply.github.com> Co-authored-by: Francis <38564764+ssssnow@users.noreply.github.com> Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com> Co-authored-by: xianzhiT <xianzhitang@tencent.com> Co-authored-by: yilian49 <43861414+yilian49@users.noreply.github.com> Co-authored-by: DangKai <dangkai4u@outlook.com> Co-authored-by: dangkai.dk <dangkai.dk@alibaba-inc.com> Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg> Co-authored-by: ll819214 <18801269230@163.com> Co-authored-by: Li Junwen <lijunwen13@hisilicon.com> Co-authored-by: zixuanzhang226 <zixuanzhang@bytedance.com> Co-authored-by: Hongbo Xu <1320612015@qq.com> Co-authored-by: shangmingc <csmthu@gmail.com> Co-authored-by: eigen <52445717+yyihuang@users.noreply.github.com> Co-authored-by: mlmz <54172054+minleminzui@users.noreply.github.com> Co-authored-by: Ruihang Lai <ruihangl@cs.cmu.edu> Co-authored-by: Meng, Peng <pengmeng@tencent.com> Co-authored-by: Mick <mickjagger19@icloud.com> Co-authored-by: yhyang201 <yhyang201@gmail.com> Co-authored-by: tarinkk <129432511+tarinkk@users.noreply.github.com> Co-authored-by: tarinkk <rt572@physics.rutger.edu> Co-authored-by: tarinkk <rt572@rutgers.physics.edu> Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com> Co-authored-by: Zheng, Beilei <beilei.zheng@intel.com> Co-authored-by: Sheng Qi <shengqi2018@pku.edu.cn> Co-authored-by: finetune <82650881+finetunej@users.noreply.github.com> Co-authored-by: Hubert Lu <55214931+hubertlu-tw@users.noreply.github.com> Co-authored-by: Kan Wu <wukanustc@gmail.com> Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com> Co-authored-by: narutolhy <582909902@qq.com> Co-authored-by: lukec <118525388+sleepcoo@users.noreply.github.com> Co-authored-by: shuaills <shishuaiuoe@gmail.com> Co-authored-by: Shenggui Li <somerlee.9@gmail.com> Co-authored-by: Yingyi Huang <yingyihuang2000@outlook.com> Co-authored-by: Simon_CQK <cqk0100@gmail.com> Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com> Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com> Co-authored-by: yych0745 <1398089567@qq.com> Co-authored-by: HandH1998 <1335248067@qq.com> Co-authored-by: 弋云 <yiyun.wyt@antgroup.com> Co-authored-by: walker-ai <2398833647@qq.com> Co-authored-by: Zilin Zhu <zhuzilinallen@gmail.com> Co-authored-by: srinarayan-srikanthan <srinarayan.srikanthan@intel.com> Co-authored-by: Albert <albert.zty@antgroup.com> Co-authored-by: Ziming Huang <1520787127@qq.com> Co-authored-by: ayrnb <70835312+ayrnb@users.noreply.github.com> Co-authored-by: HydraQYH <QYH820@Outlook.com> Co-authored-by: ronnie_zheng <zl19940307@163.com> Co-authored-by: Maksim <makcum888e@mail.ru> Co-authored-by: VDV1985 <vladdv85@mail.ru> Co-authored-by: ispobock <ispobaoke@gmail.com> Co-authored-by: TianyuZhang1214 <tianyuzhang1214@163.com> Co-authored-by: alpha-baby <fujianhao1997@qq.com> Co-authored-by: Yuchen Cheng <rudeigerc@gmail.com> Co-authored-by: Kay Yan <kay.yan@daocloud.io> Co-authored-by: Caproni <40862361+Capronir@users.noreply.github.com> Co-authored-by: Ximingwang-09 <72070413+Ximingwang-09@users.noreply.github.com> Co-authored-by: 纬杭 <ximing.wxm@antgroup.com> Co-authored-by: zyksir <zyksir@outlook.com> Co-authored-by: SijiaYang <yangsijia.614@bytedance.com> Co-authored-by: yicwang <yichen.wang@bytedance.com> Co-authored-by: Leng Yue <lengyue@lengyue.me> Co-authored-by: Qi Yuhang <45795032+HydraQYH@users.noreply.github.com> Co-authored-by: Gang Chen <13298548+MoonBall@users.noreply.github.com> Co-authored-by: Pranjal Shankhdhar <pranjal.ssh@gmail.com> Co-authored-by: jay <jthakur@habana.ai>
shuaills
pushed a commit
to shuaills/sglang
that referenced
this pull request
Jul 21, 2025
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.
Motivation
I use flashinfer
27060628c32e1217e27564adf24e33273f4c8287commit to test.In b200:
Acc:
main:
pr:
13.5us->8.7us.
end2end benchmark
Refer to trt-llm , I change
max_token_numto 1024 and get a better result:bs=1, 3.4%+
bs=8, 5%+
bs=16, 3.6+%
Modifications
Checklist