Optimize Hopper CUTLASS FP8 Blockwise Grouped GEMM Kernel in Small K Scenario #7782

HydraQYH · 2025-07-05T02:13:56Z

Motivation

Follow #7278
When K in GEMM problem size is small, CUTLASS Kernel shows suboptimal performance. The reason is that when K is small, the execution time of Mainloop is very short and Epilogue is difficult to be overlapped by Mainloop. In CUTLASS, Epilogue performs unnecessary LinearCombination, which further degrades performance.
We compared the nsight-compute profile reports of DeepGEMM and CUTLASS after aligning TileShape. The results showed that in the Small K scenario, the number of FFMA instructions executed by CUTLASS far exceeded that of DeepGEMM.

Therefore, we optimized the unnecessary LinearCombination in Epilogue.

Modifications

Only sgl-kernel/csrc/moe/fp8_blockwise_moe_kernel.cu:

Use CUTLASS Sm90EVT to define an identity op in Epilogue
When K is extremely small, the Cooperative Kernel has better performance, probably because TMA data copying is more efficient. Therefore, the Cooperative Kernel is used when K < 256.

Checklist

Format your code according to the Code Formatting with Pre-Commit.
Lint done:
Add unit tests as outlined in the Running Unit Tests.
Unitest passed:
Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
Before optimization:

After optimization:
For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.

…tive when k < 256.

gemini-code-assist

Summary of Changes

Hello @HydraQYH, 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 enhancing the performance of FP8 Blockwise Grouped GEMM operations on Hopper architecture (SM90) when dealing with small K dimensions. My changes involve optimizing the epilogue phase to remove redundant computations and implementing a dynamic kernel dispatch strategy that selects a more efficient 'Cooperative Kernel' for very small K values, leading to improved throughput as demonstrated by the provided benchmarks.

Highlights

Epilogue Optimization for Small K: I've optimized the CUTLASS Hopper FP8 Blockwise Grouped GEMM kernel by replacing the LinearCombination epilogue operation with an Identity operation using Sm90EVT. This change specifically targets scenarios where the K dimension (inner product dimension) is small, as the original LinearCombination was found to be an unnecessary performance bottleneck in these cases, preventing proper overlap with the main GEMM computation.
Conditional Kernel Dispatch for K Dimension: I've introduced a conditional dispatch mechanism within sm90_fp8_blockwise_group_mm_dispatch_shape to select the optimal CUTLASS kernel configuration based on the K dimension. For a.size(1) > 128, the existing MmaConfig0 is used. For a.size(1) <= 128 (small K), a new MmaConfig1 is now employed, which utilizes a Cooperative kernel schedule (KernelPtrArrayTmaWarpSpecializedCooperativeFP8BlockScaledAccum and EpiloguePtrArrayTmaWarpSpecializedCooperative) for better performance, likely due to more efficient TMA data copying.
Refined Kernel Dispatch Logic: The top-level fp8_blockwise_scaled_grouped_mm function no longer has a K size check (a.size(1) > 256) before calling sm90_fp8_blockwise_group_mm_dispatch_shape. This allows the more granular K-size-based kernel selection to occur within the dispatch_shape function itself, simplifying the overall dispatch flow and ensuring the optimized kernels are always considered for SM90 architectures.

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.

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. ↩

gemini-code-assist

Code Review

This pull request optimizes the Hopper CUTLASS FP8 Blockwise Grouped GEMM kernel for small K scenarios by replacing the LinearCombination epilogue with an identity operation and using a cooperative kernel for small K values. The review focuses on maintainability, code clarity, and verifying the correctness of changes.

gemini-code-assist · 2025-07-05T02:15:38Z

sgl-kernel/csrc/moe/fp8_blockwise_moe_kernel.cu

+  if (a.size(1) > 128) {
+    run_get_group_gemm_starts<MmaConfig0::LayoutSFA, MmaConfig0::LayoutSFB, MmaConfig0::ScaleConfig>(
+        expert_offsets,
+        a_ptrs,
+        b_ptrs,
+        out_ptrs,
+        a_scales_ptrs,
+        b_scales_ptrs,
+        a,
+        b,
+        output,
+        scales_a,
+        scales_b,
+        layout_sfa,
+        layout_sfb,
+        problem_sizes,
+        problem_sizes_transpose);
+    launch_sm90_fp8_blockwise_scaled_group_mm<OutType, MmaConfig0, cutlass::layout::RowMajor>(
+        out_ptrs,
+        a_ptrs,
+        b_ptrs,
+        a_scales_ptrs,
+        b_scales_ptrs,
+        stride_a,
+        stride_b,
+        stride_c,
+        layout_sfa,
+        layout_sfb,
+        problem_sizes,
+        expert_offsets,
+        workspace);
+  } else {
+    // Small K
+    run_get_group_gemm_starts<MmaConfig1::LayoutSFA, MmaConfig1::LayoutSFB, MmaConfig1::ScaleConfig>(
+        expert_offsets,
+        a_ptrs,
+        b_ptrs,
+        out_ptrs,
+        a_scales_ptrs,
+        b_scales_ptrs,
+        a,
+        b,
+        output,
+        scales_a,
+        scales_b,
+        layout_sfa,
+        layout_sfb,
+        problem_sizes,
+        problem_sizes_transpose);
+    launch_sm90_fp8_blockwise_scaled_group_mm<OutType, MmaConfig1, cutlass::layout::RowMajor>(
+        out_ptrs,
+        a_ptrs,
+        b_ptrs,
+        a_scales_ptrs,
+        b_scales_ptrs,
+        stride_a,
+        stride_b,
+        stride_c,
+        layout_sfa,
+        layout_sfb,
+        problem_sizes,
+        expert_offsets,
+        workspace);
+  }


There's significant code duplication in the if and else blocks. The core logic is the same, only the MmaConfig type changes. Refactor this into a helper function templated on the MmaConfig type to improve maintainability.

template <typename OutType, typename MmaConfig> void run_grouped_gemm( // ... arguments ... ) { run_get_group_gemm_starts<typename MmaConfig::LayoutSFA, typename MmaConfig::LayoutSFB, typename MmaConfig::ScaleConfig>( // ... args ... ); launch_sm90_fp8_blockwise_scaled_group_mm<OutType, MmaConfig, cutlass::layout::RowMajor>( // ... args ... ); } // In sm90_fp8_blockwise_group_mm_dispatch_shape: if (a.size(1) > 128) { run_grouped_gemm<OutType, MmaConfig0>(...); } else { // Small K run_grouped_gemm<OutType, MmaConfig1>(...); }

Make sense, we can build a marco to do this @HydraQYH

gemini-code-assist · 2025-07-05T02:15:38Z

sgl-kernel/csrc/moe/fp8_blockwise_moe_kernel.cu

+  static constexpr auto RoundStyle = cutlass::FloatRoundStyle::round_to_nearest;
+  using CustomEVTIdentity =  // acc
+      cutlass::epilogue::fusion::Sm90EVT<
+          cutlass::epilogue::fusion::
+              Sm90Compute<cutlass::epilogue::thread::Identity, ElementD, ElementAccumulator, RoundStyle>,
+          cutlass::epilogue::fusion::Sm90AccFetch>;


Consider adding a comment to clarify the purpose of CustomEVTIdentity. For example: "Defines an identity operation for the epilogue to avoid unnecessary linear combination when K is small."

Is this epilogue op used to accumulate results along the k dim? Thanks.

No. Accumulating results along the K dim happens in Mainloop. You can refer to this code: https://github.com/NVIDIA/cutlass/blob/a1aaf2300a8fc3a8106a05436e1a2abad0930443/include/cutlass/gemm/collective/sm90_mma_array_tma_gmma_ss_warpspecialized_fp8_blockwise_scaling.hpp#L723

In FP8 blockwise scaling kernel, there are two kinds of accumulate:

TensorCore accumulate: hidden in cute::gemm

CUDA Core accumulate: Just look GmmaFP8Accumulation accumulation(accum, ScalePromotionInterval, size<2>(tCrA)); in CUTLASS.

gemini-code-assist · 2025-07-05T02:15:38Z

sgl-kernel/csrc/moe/fp8_blockwise_moe_kernel.cu

@@ -641,7 +692,7 @@ void fp8_blockwise_scaled_grouped_mm(
 #endif

 #if defined(CUTLASS_ARCH_MMA_SM90_SUPPORTED) && defined(CUTLASS_ARCH_MMA_MODIFIABLE_TMA_SM90_SUPPORTED)
-  if (sm_version == 90 && a.size(1) > 256) {
+  if (sm_version == 90) {


Removing the size check a.size(1) > 256 might impact performance in scenarios where the original condition was beneficial. Verify that removing this condition does not introduce performance regressions in other cases.

gemini-code-assist · 2025-07-05T02:15:38Z

sgl-kernel/csrc/moe/fp8_blockwise_moe_kernel.cu

+      can_implement, "No implemented fp8_blockwise_scaled_mm for current compute capability: ", sm_version);
 }


The removed a.size(1) check in the TORCH_CHECK_NOT_IMPLEMENTED macro suggests that the K size is no longer a factor in determining whether an implementation exists. Confirm that this change aligns with the intended behavior and that the error message accurately reflects the conditions under which the function might not be implemented.

yue-zhang-2025 · 2025-07-05T04:20:24Z

sgl-kernel/csrc/moe/fp8_blockwise_moe_kernel.cu

+  struct MmaConfig1 {
+    using ElementA = cutlass::float_e4m3_t;
+    using MmaTileShape = Shape<_128, _128, _128>;
+    using ClusterShape = Shape<_1, _2, _1>;


just curious: wondering how did we determine the tile shape and cluster shape here? any intuition for these numbers?

According to the actual business scenario, set a larger TileShape as much as possible to ensure that the calculation time is greater than the data loading time, which makes it easier to fully utilize the computing power. In most cases, you can just refer to CUTLASS Examples

Pingpong's TileShape is generally half of Cooperative's. This is to make Pingpong and Cooperative have similar shared memory consumption and register pressure.

The best cluster size is 2, which can not only use TMA to reduce the pressure on L2 Cache bandwidth, but also prevent hardware overheating from causing frequency reduction or SM Core Down.

zhyncs · 2025-07-05T05:25:35Z

Thank you @yue-zhang-2025 and @Alcanderian for the review. Let's merge this first. @HydraQYH, can you please fix the comments in the follow-up? Thank you!

…Scenario (sgl-project#7782)

@mickqian

* 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>

…Scenario (sgl-project#7782)

HydraQYH added 2 commits July 5, 2025 09:09

Optimize small k gemm: 1. Use identity op in epilogue. 2. Use Coopera…

b72dd52

…tive when k < 256.

Lint code.

aa690b1

HydraQYH requested review from zhyncs, ispobock, HandH1998, BBuf, yizhang2077, merrymercy, FlamingoPg and HaiShaw as code owners July 5, 2025 02:13

gemini-code-assist bot reviewed Jul 5, 2025

View reviewed changes

zhyncs assigned Alcanderian, BBuf and yue-zhang-2025 Jul 5, 2025

zhyncs added the high priority label Jul 5, 2025

zhyncs assigned AniZpZ Jul 5, 2025

yue-zhang-2025 approved these changes Jul 5, 2025

View reviewed changes

Alcanderian approved these changes Jul 5, 2025

View reviewed changes

zhyncs merged commit 8e9fb43 into sgl-project:main Jul 5, 2025
32 of 39 checks passed

This was referenced Jul 11, 2025

[fix]Update unitest for fp8_blockwise_scaled_grouped_mm kernel #7932

Merged

[feat]Support fusion kernel for constructing quant input and scale factor for fp8_blockwise_scaled_grouped_mm #8023

Merged

chenxijun1029 pushed a commit to chenxijun1029/sglang that referenced this pull request Jul 17, 2025

Optimize Hopper CUTLASS FP8 Blockwise Grouped GEMM Kernel in Small K …

b474bbd

…Scenario (sgl-project#7782)

shuaills pushed a commit to shuaills/sglang that referenced this pull request Jul 21, 2025

Optimize Hopper CUTLASS FP8 Blockwise Grouped GEMM Kernel in Small K …

71d9d85

…Scenario (sgl-project#7782)

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Optimize Hopper CUTLASS FP8 Blockwise Grouped GEMM Kernel in Small K Scenario #7782

Optimize Hopper CUTLASS FP8 Blockwise Grouped GEMM Kernel in Small K Scenario #7782

Uh oh!

HydraQYH commented Jul 5, 2025

Uh oh!

gemini-code-assist bot left a comment

Uh oh!

gemini-code-assist bot left a comment

Uh oh!

gemini-code-assist bot Jul 5, 2025

Uh oh!

Alcanderian Jul 5, 2025

Uh oh!

gemini-code-assist bot Jul 5, 2025

Uh oh!

Edenzzzz Jul 6, 2025

Uh oh!

HydraQYH Jul 7, 2025

Uh oh!

HydraQYH Jul 7, 2025

Uh oh!

gemini-code-assist bot Jul 5, 2025

Uh oh!

gemini-code-assist bot Jul 5, 2025

Uh oh!

yue-zhang-2025 Jul 5, 2025

Uh oh!

HydraQYH Jul 5, 2025

Uh oh!

zhyncs commented Jul 5, 2025

Uh oh!

Uh oh!

Uh oh!

		can_implement, "No implemented fp8_blockwise_scaled_mm for current compute capability: ", sm_version);
		}

Optimize Hopper CUTLASS FP8 Blockwise Grouped GEMM Kernel in Small K Scenario #7782

Optimize Hopper CUTLASS FP8 Blockwise Grouped GEMM Kernel in Small K Scenario #7782

Uh oh!

Conversation

HydraQYH commented Jul 5, 2025

Motivation

Modifications

Checklist

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist bot Jul 5, 2025

Choose a reason for hiding this comment

Uh oh!

Alcanderian Jul 5, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Jul 5, 2025

Choose a reason for hiding this comment

Uh oh!

Edenzzzz Jul 6, 2025

Choose a reason for hiding this comment

Uh oh!

HydraQYH Jul 7, 2025

Choose a reason for hiding this comment

Uh oh!

HydraQYH Jul 7, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Jul 5, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Jul 5, 2025

Choose a reason for hiding this comment

Uh oh!

yue-zhang-2025 Jul 5, 2025

Choose a reason for hiding this comment

Uh oh!

HydraQYH Jul 5, 2025

Choose a reason for hiding this comment

Uh oh!

zhyncs commented Jul 5, 2025

Uh oh!

Uh oh!

Uh oh!