xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 22:28:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix] Revert ROCm Custom Paged Attention Env Flag Check (#17022)

Browse Source 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
vllmellm 2025-04-23 10:17:48 +08:00 committed by GitHub
parent 1e013fa388
commit 7e081ba7ca
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/platforms/rocm.py
View File

@ -118,6 +118,7 @@ def use_rocm_custom_paged_attention(qtype: torch.dtype, head_size: int,
and (head_size == 64 or head_size == 128) and (head_size == 64 or head_size == 128)
and (block_size == 16 or block_size == 32) and (block_size == 16 or block_size == 32)
and (gqa_ratio >= 1 and gqa_ratio <= 16) and max_seq_len <= 32768 and (gqa_ratio >= 1 and gqa_ratio <= 16) and max_seq_len <= 32768
and (envs.VLLM_ROCM_CUSTOM_PAGED_ATTN)
and not (envs.VLLM_ROCM_USE_AITER_PAGED_ATTN and not (envs.VLLM_ROCM_USE_AITER_PAGED_ATTN
and envs.VLLM_ROCM_USE_AITER)) and envs.VLLM_ROCM_USE_AITER))