Convert cu_seqlens to CPU for npu_flash_attention_unpad operator#15434
Merged
iforgetmyname merged 15 commits intosgl-project:mainfrom Jan 4, 2026
Merged
Convert cu_seqlens to CPU for npu_flash_attention_unpad operator#15434iforgetmyname merged 15 commits intosgl-project:mainfrom
iforgetmyname merged 15 commits intosgl-project:mainfrom
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
yuan-luo
reviewed
Dec 19, 2025
| self.act = ACT2FN[hidden_act] | ||
| self.hidden_act = hidden_act | ||
| if self.hidden_act == "silu": | ||
| from sglang.srt.layers.activation import SiluAndMul |
Collaborator
There was a problem hiding this comment.
Move imports to the top of the file.
* 'main' of https://github.com/sgl-project/sglang: (136 commits) fix: unreachable error check in retraction (sgl-project#15433) [sgl-kernel] chore: update deepgemm version (sgl-project#13402) [diffusion] multi-platform: support diffusion on amd and fix encoder loading on MI325 (sgl-project#13760) [amd] Add deterministic all-reduce kernel for AMD (ROCm) (sgl-project#15340) [diffusion] refactor: refactor _build_req_from_sampling to use shallow_asdict (sgl-project#13782) Add customized sampler registration (sgl-project#15423) Update readme (sgl-project#15425) Fix Mindspore model import warning (sgl-project#15287) [Feature] Xiaomi `MiMo-V2-Flash` day0 support (sgl-project#15207) [diffusion] profiling: add bench_serving.py and VBench (sgl-project#15410) [DLLM] Fix dLLM regression (sgl-project#15371) [Deepseek V3.2] Fix Deepseek MTP in V1 mode (sgl-project#15429) chore: update CI_PERMISSIONS (sgl-project#15431) [DLLM] Add CI for diffusion LLMs (sgl-project#14723) Support using different attention backend for draft decoding. (sgl-project#14843) feat(dsv32): better error handling for DeepSeek-v3.2 encoder (sgl-project#14353) tiny fix lint on main (sgl-project#15424) multimodal: precompute hash for MultimodalDataItem (sgl-project#14354) [AMD] Clear pre-built AITER kernels and warmup to prevent segfaults and test timeouts (sgl-project#15318) [Performance] optimize NSA backend metadata computation for multi-step speculative decoding (sgl-project#14781) ...
Collaborator
|
please fix lint by |
iforgetmyname
added a commit
that referenced
this pull request
Dec 26, 2025
Liwansi
added a commit
to iforgetmyname/sglang
that referenced
this pull request
Dec 29, 2025
…glang into eagle-sche * 'ifmn/eagle-dp-attn' of https://github.com/sgl-project/sglang: (22 commits) dp scheduler enhance support with chunked prefill (sgl-project#16071) modify suffix decoding CI dependency update (sgl-project#16063) fix rotary_embedding init npu (sgl-project#16011) feat: bugfix and accuracy fix for stablelm2_1_6b (sgl-project#15932) Update model and feature support for Ascend NPU (sgl-project#16005) Bugfix for Llama4 (sgl-project#15929) Bugfix for ds-vl2 (sgl-project#15894) gme qwen vl runners fix (sgl-project#15899) add profiling in scheduler (sgl-project#15876) llama use triton rope op (sgl-project#15855) suffix decoding adapt npu suffix decoding adapt npu Add suffix decoding speculative algorithm from feature 13553 cherry sgl-project#15434: qwen3 vl performance update cherry sgl-project#15597: fix Qwen3-VL-30B-A3B-Instruct accuracy loss [Schedule] bug fix for schedule enhancer (sgl-project#15834) minilb support roundrobin (sgl-project#15824) fix torchair compile issue cherry sgl-project#15187: lora fix ... # Conflicts: # python/sglang/srt/managers/scheduler.py # python/sglang/srt/managers/scheduler_enhancer.py
Collaborator
|
/tag-and-rerun-ci |
Comment on lines
+490
to
+493
| if is_npu(): | ||
| cu_seqlens = cu_seqlens.to("cpu") | ||
| else: | ||
| cu_seqlens = cu_seqlens.to(self.device, non_blocking=True) |
Collaborator
There was a problem hiding this comment.
Suggested change
| if is_npu(): | |
| cu_seqlens = cu_seqlens.to("cpu") | |
| else: | |
| cu_seqlens = cu_seqlens.to(self.device, non_blocking=True) | |
| if not is_npu(): | |
| xxx | |
| else: | |
| xxx |
iforgetmyname
approved these changes
Jan 3, 2026
JiaruiChang5268
pushed a commit
to JiaruiChang5268/sglang
that referenced
this pull request
Jan 10, 2026
YChange01
pushed a commit
to YChange01/sglang
that referenced
this pull request
Jan 13, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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
In order to improve the performance of VisionAscendAttention, we convert cu_seqlens to CPU before the first transformer layer, because converting it to CPU per layer would interrupt operator dispatch and cause kernel bubbles.
Modifications
Accuracy Tests
All modifications do not affect the precision
Benchmarking and Profiling
Checklist