Skip to content

GitLab

Commit 6b58062d authored by zhuwenwen's avatar zhuwenwen
Browse files

fix index

parent a3695a2b
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/layers/fused_moe/fused_moe.py
View file @ 6b58062d
...@@ -51,7 +51,7 @@ if envs.VLLM_USE_GLOBAL_CACHE13: ...@@ -51,7 +51,7 @@ if envs.VLLM_USE_GLOBAL_CACHE13:
moe_cache_singleton = None moe_cache_singleton = None
arch_name = torch.cuda.get_device_properties("cuda").gcnArchName.split(':')[0] arch_name = torch.cuda.get_device_properties("cuda").gcnArchName.split(':')[0]
arch_cu = torch.cuda.get_device_properties(torch.cuda.current_device()).multi_processor_count arch_cu = torch.cuda.get_device_properties(torch.cuda.current_device()).multi_processor_count
@torch.compile @torch.compile
def moe_sum_reduce_torch_compile(x, out, routed_scaling_factor): def moe_sum_reduce_torch_compile(x, out, routed_scaling_factor):
......
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