Skip to content

GitLab

"vllm/model_executor/models/qwen_vl.py" did not exist on "083b80eaa4b8c2af38c8e5e08bcbb85733c480fa"
Unverified Commit 28566d73 authored by Hongxia Yang's avatar Hongxia Yang Committed by GitHub
Browse files

[ROCm] remove unsupported archs from rocm triton flash-attention supported list (#17536) 


Signed-off-by: default avatarHongxia Yang <hongxia.yang@amd.com>
parent 98060b00
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/attention/ops/triton_flash_attention.py
View file @ 28566d73
......@@ -650,7 +650,7 @@ def get_general_autotune_configs():
def has_cdna_target():
ROCM_CDNA_TARGETS = ["gfx940", "gfx941", "gfx942", "gfx90a", "gfx908"]
ROCM_CDNA_TARGETS = ["gfx942", "gfx90a", "gfx908"]
return triton.runtime.driver.active.get_current_target(
).arch in ROCM_CDNA_TARGETS
......
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