Skip to content

GitLab

Unverified Commit aa5053e3 authored by Egor's avatar Egor Committed by GitHub
Browse files

[Doc] Fixed shape description for fused_batched_moe.py (#25668) 


Signed-off-by: default avatarEgor <e.a.krivov@gmail.com>
parent 79aa2446
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/layers/fused_moe/fused_batched_moe.py
View file @ aa5053e3
...@@ -355,7 +355,7 @@ def batched_triton_kernel( ...@@ -355,7 +355,7 @@ def batched_triton_kernel(
def invoke_moe_batched_triton_kernel( def invoke_moe_batched_triton_kernel(
A: torch.Tensor, # [E, max_tokens, K] A: torch.Tensor, # [E, max_tokens, K]
B: torch.Tensor, # [E, K, N] B: torch.Tensor, # [E, N, K]
C: torch.Tensor, # [E, max_tokens, N] C: torch.Tensor, # [E, max_tokens, N]
expert_num_tokens: torch.Tensor, # [E] expert_num_tokens: torch.Tensor, # [E]
compute_type: tl.dtype, compute_type: tl.dtype,
......
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