Skip to content

GitLab

"ssh:/git@developer.sourcefind.cn:2222/OpenDAS/vllm_cscc.git" did not exist on "e3a0f21e6ce78268865cafcdc3dc58c7a80dbc57"
Unverified Commit d11ec124 authored by Jee Jee Li's avatar Jee Jee Li Committed by GitHub
Browse files

[Bench] Add qwen-next in benchmark_moe.py (#24661) 


Signed-off-by: default avatarJee Jee Li <pandaleefree@gmail.com>
parent f5107158
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 1 deletion
benchmarks/kernels/benchmark_moe.py
View file @ d11ec124
...@@ -594,7 +594,11 @@ def main(args: argparse.Namespace): ...@@ -594,7 +594,11 @@ def main(args: argparse.Namespace):
E = config.n_routed_experts E = config.n_routed_experts
topk = config.num_experts_per_tok topk = config.num_experts_per_tok
intermediate_size = config.moe_intermediate_size intermediate_size = config.moe_intermediate_size
elif config.architectures[0] in ("Qwen2MoeForCausalLM", "Qwen3MoeForCausalLM"): elif config.architectures[0] in (
"Qwen2MoeForCausalLM",
"Qwen3MoeForCausalLM",
"Qwen3NextForCausalLM",
):
E = config.num_experts E = config.num_experts
topk = config.num_experts_per_tok topk = config.num_experts_per_tok
intermediate_size = config.moe_intermediate_size intermediate_size = config.moe_intermediate_size
......
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