Skip to content

GitLab

Unverified Commit 5cdd6645 authored by Lucas Wilkinson's avatar Lucas Wilkinson Committed by GitHub
Browse files

[BugFix] Fix assert in `build_for_cudagraph_capture` (#29893) 


Signed-off-by: default avatarLucas Wilkinson <lwilkins@redhat.com>
parent 5f67361f
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/v1/worker/gpu_model_runner.py
View file @ 5cdd6645
...@@ -4000,7 +4000,7 @@ class GPUModelRunner( ...@@ -4000,7 +4000,7 @@ class GPUModelRunner(
num_reqs=num_reqs_padded, num_reqs=num_reqs_padded,
max_query_len=max_query_len, max_query_len=max_query_len,
ubatch_slices=ubatch_slices, ubatch_slices=ubatch_slices,
for_cudagraph_capture=True, for_cudagraph_capture=is_graph_capturing,
) )
with self.maybe_dummy_run_with_lora( with self.maybe_dummy_run_with_lora(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment