xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-05 07:47:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bug] Fix Shape Validation for Fallback while Enabling E8M0 for DeepGEMM (#26322)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye 2025-10-07 13:50:30 -04:00 committed by GitHub
parent 29fd2662ba
commit 8f36850f73
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py
View File

@ -143,7 +143,7 @@ class TritonOrDeepGemmExperts(mk.FusedMoEPermuteExpertsUnpermute):
apply_router_weight_on_input: bool,
):
use_deep_gemm = self.allow_deep_gemm and (
_valid_deep_gemm(hidden_states, w1, w2) or is_deep_gemm_e8m0_used()
is_deep_gemm_e8m0_used() or _valid_deep_gemm(hidden_states, w1, w2)
)
experts = self.deep_gemm_expert if use_deep_gemm else self.triton_expert