xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-23 06:37:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix] Fix assert in build_for_cudagraph_capture (#29893)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
This commit is contained in:
Lucas Wilkinson 2025-12-02 19:56:54 -05:00 committed by GitHub
parent 5f67361fd1
commit 5cdd664509
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/worker/gpu_model_runner.py
View File

@ -4000,7 +4000,7 @@ class GPUModelRunner(
num_reqs=num_reqs_padded,
max_query_len=max_query_len,
ubatch_slices=ubatch_slices,
for_cudagraph_capture=True,
for_cudagraph_capture=is_graph_capturing,
)
with self.maybe_dummy_run_with_lora(