xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-20 23:25:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

[ROCm][AITER][Bugfix] Switch AITER to use PIECEWISE_AND_FULL compilation (#25104)

Browse Source 
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
This commit is contained in:
Rohan Potdar 2025-09-18 12:46:47 -05:00 committed by GitHub
parent dc34059360
commit bbdc0f2366
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/attention/backends/rocm_aiter_fa.py
View File

@ -232,7 +232,7 @@ class AiterFlashAttentionMetadata:
class AiterFlashAttentionMetadataBuilder( class AiterFlashAttentionMetadataBuilder(
AttentionMetadataBuilder[AiterFlashAttentionMetadata]): AttentionMetadataBuilder[AiterFlashAttentionMetadata]):
cudagraph_support = AttentionCGSupport.ALWAYS cudagraph_support = AttentionCGSupport.UNIFORM_SINGLE_TOKEN_DECODE
def __init__(self, kv_cache_spec: AttentionSpec, layer_names: list[str], def __init__(self, kv_cache_spec: AttentionSpec, layer_names: list[str],
vllm_config: VllmConfig, device: torch.device): vllm_config: VllmConfig, device: torch.device):