biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc]: fixing typos in various files (#30540)

Browse Source 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Signed-off-by: Didier Durand <2927957+didier-durand@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Didier Durand
2025-12-14 11:14:37 +01:00
committed by GitHub
parent add1b9d3de
commit 1a55cfafcb
12 changed files with 17 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/layers/fused_moe/shared_fused_moe.py
View File

@@ -30,8 +30,8 @@ class SharedFusedMoE(FusedMoE):
# Disable shared expert overlap if:
# - we are using eplb, because of correctness issues
# - we are using flashinfer with DP, since there nothint to gain
# - we are using marlin kjernels
# - we are using flashinfer with DP, since there nothing to gain
# - we are using marlin kernels
self.use_overlapped = (
use_overlapped
and not (

2
vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py
View File

@@ -62,7 +62,7 @@ def choose_scaled_mm_linear_kernel(
continue
# If the current platform uses compute_capability,
# make sure the kernel supports the compute cability.
# make sure the kernel supports the compute capability.
is_supported, reason = kernel.is_supported(compute_capability)
if not is_supported:
failure_reasons.append(f"{kernel.__name__}: {reason}")