[0.9.1][Perf] apply npu_moe_gating_top_k_softmax for moe #1902
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
loukong33
force-pushed
the
topk_softmax
branch
4 times, most recently
from
b05b8fb to
f7daac9
Compare
loukong33
force-pushed
the
topk_softmax
branch
8 times, most recently
from
2a5dcb7 to
562a001
Compare
loukong33
force-pushed
the
topk_softmax
branch
12 times, most recently
from
aeb4f15 to
39b4c9f
Compare
Signed-off-by: huangxialu <huangxialu1@huawei.com>
loukong33
changed the title
loukong33
changed the title
ganyi1996ppo
approved these changes
Jul 22, 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) ...
jianzs
pushed a commit
that referenced
this pull request
Jul 31, 2025
…LECT_GATING_TOPK_SOTFMAX_EXPERTS (#2112) backport of v0.9.1-dev: #1902 origin main npu_moe_gating_top_k_softmax: #1355 - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@055bd39 Signed-off-by: huangxialu <huangxialu1@huawei.com>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Sep 26, 2025
…LECT_GATING_TOPK_SOTFMAX_EXPERTS (vllm-project#2112) backport of v0.9.1-dev: vllm-project#1902 origin main npu_moe_gating_top_k_softmax: vllm-project#1355 - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@055bd39 Signed-off-by: huangxialu <huangxialu1@huawei.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
…LECT_GATING_TOPK_SOTFMAX_EXPERTS (vllm-project#2112) backport of v0.9.1-dev: vllm-project#1902 origin main npu_moe_gating_top_k_softmax: vllm-project#1355 - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@055bd39 Signed-off-by: huangxialu <huangxialu1@huawei.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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?
Apply torch_npu.npu_moe_gating_top_k_softmax for moe, when scoring_func is softmax.
Does this PR introduce any user-facing change?
NO
How was this patch tested?
ut.
performance:
base：
Successful requests: 200
Benchmark duration (s): 367.80
Total input tokens: 409600
Total generated tokens: 409600
Request throughput (req/s): 0.54
Output token throughput (tok/s): 1113.64
Total Token throughput (tok/s): 2227.28
apply torch_npu.npu_moe_gating_top_k_softmax：
Successful requests: 200
Benchmark duration (s): 362.59
Total input tokens: 409600
Total generated tokens: 409600
Request throughput (req/s): 0.55
Output token throughput (tok/s): 1129.64
Total Token throughput (tok/s): 2259.29