Skip to content

GitLab

Unverified Commit 8ca89548 authored by yudian0504's avatar yudian0504 Committed by GitHub
Browse files

[Bugfix][Misc]: fix graph capture for decoder (#9549)

parent f6b97293
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/worker/model_runner.py
View file @ 8ca89548
...@@ -828,7 +828,7 @@ class ModelInputForGPUBuilder(ModelRunnerInputBuilderBase[ModelInputForGPU]): ...@@ -828,7 +828,7 @@ class ModelInputForGPUBuilder(ModelRunnerInputBuilderBase[ModelInputForGPU]):
cuda_graph_pad_size = self._get_cuda_graph_pad_size( cuda_graph_pad_size = self._get_cuda_graph_pad_size(
num_seqs=len(seq_lens), num_seqs=len(seq_lens),
max_decode_seq_len=max_encoder_seq_len, max_decode_seq_len=max_decode_seq_len,
max_encoder_seq_len=max_encoder_seq_len) max_encoder_seq_len=max_encoder_seq_len)
batch_size = len(input_tokens) batch_size = len(input_tokens)
......
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