Skip to content

GitLab

Commit d4cc442a authored by zhuwenwen's avatar zhuwenwen
Browse files

update SUPPORT_TC

parent 02845513
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/utils/__init__.py
View file @ d4cc442a
...@@ -93,7 +93,7 @@ POOLING_MODEL_MAX_NUM_BATCHED_TOKENS = 32768 ...@@ -93,7 +93,7 @@ POOLING_MODEL_MAX_NUM_BATCHED_TOKENS = 32768
MULTIMODAL_MODEL_MAX_NUM_BATCHED_TOKENS = 5120 MULTIMODAL_MODEL_MAX_NUM_BATCHED_TOKENS = 5120
GPU_ARCH = torch.cuda.get_device_properties("cuda").gcnArchName GPU_ARCH = torch.cuda.get_device_properties("cuda").gcnArchName
SUPPORT_TC = any(arch in GPU_ARCH for arch in ["gfx928", "gfx936"]) SUPPORT_TC = any(arch in GPU_ARCH for arch in ["gfx928", "gfx936", "gfx938"])
# Constants related to forcing the attention backend selection # Constants related to forcing the attention backend selection
......
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