biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[MISC] cudagraph_capture_sizes related improvements (#26016)

Browse Source 
Signed-off-by: fhl <2410591650@qq.com>
Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
fhl2000
2025-10-24 20:11:05 +08:00
committed by GitHub
parent 435be10db9
commit 284cc92275
14 changed files with 303 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/attention/backends/gdn_attn.py
View File

@@ -87,7 +87,7 @@ class GDNAttentionMetadataBuilder(AttentionMetadataBuilder[GDNAttentionMetadata]
)
self.decode_cudagraph_max_bs = min(
self.vllm_config.scheduler_config.max_num_seqs * (self.num_spec + 1),
self.compilation_config.max_capture_size,
self.compilation_config.max_cudagraph_capture_size,
)
self.spec_state_indices_tensor = torch.empty(