[0.9.1][Perf] Use fused ops npu_top_k_top_p #1920
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Pr0Wh1teGivee
force-pushed
the
sampler_091
branch
from
2bb06c5 to
f946e11
Compare
Pr0Wh1teGivee
changed the title
…huaweicloud.com/ascend/repos/pypi/torch-npu/ Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Pr0Wh1teGivee
force-pushed
the
sampler_091
branch
from
f946e11 to
7966750
Compare
wangxiyuan
changed the title
ganyi1996ppo
approved these changes
Jul 23, 2025
845473182
added a commit
to 845473182/vllm-ascend
that referenced
this pull request
Jul 23, 2025
* br_eplb_into_v091: (29 commits) add eplb design doc merge update in eplb branch dynamic eplb [0.9.1][Perf] Use fused ops npu_top_k_top_p (vllm-project#1920) [0.9.1][PD][Perf] Avoid performing cpu all_reduce in disaggregated-prefill scenario. (vllm-project#1644) [0.9.1][BugFix] Fix bug in path_decorator when engine v0 (vllm-project#1919) [0.9.1][Perf] apply npu_moe_gating_top_k_softmax for moe (vllm-project#1902) [0.9.1][bugfix] W4A8 does not currently support apply_mlp_decode (vllm-project#1910) [0.9.1][CI] Pin vllm version to v0.9.1 to make mypy check passed (vllm-project#1904) [0.9.1][Dist][Bugfix] Fix mc2 process group to resolve self.cpu_group is None (vllm-project#1831) [0.9.1][Perf]Remove NZ of kv_b_proj in Deepseek MLA. (vllm-project#1872) [0.9.1][bugfix] V0.9.1 fix rope accruracy bug for deepseek model (vllm-project#1887) [0.9.1] Fix wheel glibc version incompatibility (vllm-project#1808) [BUGFIX][v0.9.1] repair moe error when set multistream. (vllm-project#1882) [BUGFIX][v0.9.1] ep_group is not equal to word_size in some cases. (vllm-project#1862) [BUGFIX][v0.9.1] fix enable_multistream_moe bug when DBO is enabled (… (vllm-project#1827) [0.9.1]optmize rope in qwen2 (vllm-project#1782) [BugFix] Fix flashcomm_v1 when engine v0 (vllm-project#1859) [BugFix] Fix decorator patch (vllm-project#1858) [0.9.1][Fix] Fix DeepSeek OOM issue in extreme `--gpu-memory-utilization` scenario (vllm-project#1829) ...
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
What this PR does / why we need it?
Use fused ops torch_npu.npu_top_k_top_p(logits, p, k) when p and k are not None, otherwise fallback to the original one. The replacement will take place automatically when VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE=1 .
This patch are using npu_top_k_top_p which required torch_npu>=2.5.1.post1.dev20250619
This modification is backport from https://github.com/vllm-project/vllm-ascend/blob/main/vllm_ascend/patch/worker/patch_common/patch_sampler.py
PR：#1308
Does this PR introduce any user-facing change?
No
How was this patch tested?
ut & e2e