Fix typos in comments across multiple files (#30345)
Signed-off-by: Wilson Wu <iwilsonwu@gmail.com> Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
@@ -4871,7 +4871,7 @@ class GPUModelRunner(
|
||||
# we need to adjust the cudagraph sizes to be a multiple of the uniform
|
||||
# decode query length to avoid: https://github.com/vllm-project/vllm/issues/28207
|
||||
# temp-fix: https://github.com/vllm-project/vllm/issues/28207#issuecomment-3504004536
|
||||
# Will be removed in the near future when we have seperate cudagraph capture
|
||||
# Will be removed in the near future when we have separate cudagraph capture
|
||||
# sizes for decode and mixed prefill-decode.
|
||||
if (
|
||||
cudagraph_mode.decode_mode() == CUDAGraphMode.FULL
|
||||
|
||||
Reference in New Issue
Block a user