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

[Doc]: fix typos in various files (#28863)

Browse Source 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
This commit is contained in:
Didier Durand
2025-11-18 05:32:14 +01:00
committed by GitHub
parent bf9e1e8767
commit 083cf326dc
6 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/lora/ops/triton_ops/fused_moe_lora_op.py
View File

@@ -154,7 +154,7 @@ def _fused_moe_lora_kernel(
k_remaining = K - k * (BLOCK_SIZE_K * SPLIT_K)
# pre-fetch lora weight
b = tl.load(b_ptrs, mask=offs_k[:, None] < k_remaining, other=0.0)
# GDC wait waits for ALL programs in the the prior kernel to complete
# GDC wait waits for ALL programs in the prior kernel to complete
# before continuing.
if USE_GDC and not IS_PRIMARY:
tl.extra.cuda.gdc_wait()