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

[Doc]: fix typos in Python comments (#24294)

Browse Source 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Didier Durand
2025-09-06 04:41:12 +02:00
committed by GitHub
parent 35efa70297
commit 35bf193864
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/layer.py
View File

@@ -710,7 +710,7 @@ def determine_expert_map(
# Create a tensor of size num_experts filled with -1
expert_map = torch.full((global_num_experts, ), -1, dtype=torch.int32)
# Create a expert map for the local experts
# Create an expert map for the local experts
start_idx = ep_rank * base_experts + min(ep_rank, remainder)
expert_map[start_idx:start_idx + local_num_experts] = torch.arange(
0, local_num_experts, dtype=torch.int32)
@@ -806,7 +806,7 @@ class FusedMoE(CustomOp):
self.global_num_experts = num_experts + num_redundant_experts
# we padding globally so EP buffer allocation works
# we are padding globally so EP buffer allocation works
if quant_config and quant_config.get_name() == "mxfp4":
from vllm.model_executor.layers.quantization.mxfp4 import ( # noqa: E501
should_use_flashinfer_mxfp4)