[BugFix] Fix some issues caused by the ascending order of cudagraph_capture_sizes (#4338)
### What this PR does / why we need it?
In [#26016](https://github.com/vllm-project/vllm/pull/26016), vllm
change the `cudagraph_capture_sizes` to be in ascending order. This PR
fixes related issues caused by this.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: Angazenn <supperccell@163.com>
This commit is contained in:
@@ -433,7 +433,13 @@ def _is_default_capture_sizes(vllm_config: VllmConfig) -> bool:
|
||||
cudagraph_capture_sizes += list(
|
||||
range(256, max_cudagraph_capture_size + 1, 16))
|
||||
|
||||
if sorted(cudagraph_capture_sizes, reverse=True) == \
|
||||
if vllm_version_is("0.11.0"):
|
||||
target_cudagraph_capture_sizes = sorted(cudagraph_capture_sizes,
|
||||
reverse=True)
|
||||
else:
|
||||
# in newer version, vVLLM use ascending order of cudagraph_capture_sizes.
|
||||
target_cudagraph_capture_sizes = sorted(cudagraph_capture_sizes)
|
||||
if target_cudagraph_capture_sizes == \
|
||||
vllm_config.compilation_config.cudagraph_capture_sizes:
|
||||
return True
|
||||
|
||||
|
||||
Reference in New Issue
Block a user