biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

GLM-4 Update (#20736)

Browse Source 
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Lu Fang <fanglu@fb.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Lu Fang <fanglu@fb.com>
This commit is contained in:
Yuxuan Zhang
2025-07-20 06:40:31 +08:00
committed by GitHub
parent 2e8cbb58f3
commit 10eb24cc91
14 changed files with 2006 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
benchmarks/kernels/benchmark_moe.py
View File

@@ -576,7 +576,11 @@ def main(args: argparse.Namespace):
topk = config.num_experts_per_tok
intermediate_size = config.intermediate_size
shard_intermediate_size = 2 * intermediate_size // args.tp_size
elif config.architectures[0] in ("DeepseekV3ForCausalLM", "DeepseekV2ForCausalLM"):
elif config.architectures[0] in (
"DeepseekV3ForCausalLM",
"DeepseekV2ForCausalLM",
"Glm4MoeForCausalLM",
):
E = config.n_routed_experts
topk = config.num_experts_per_tok
intermediate_size = config.moe_intermediate_size