feat: support glm4 tuning (#8473)

2025-07-28 14:32:58 -07:00
parent 9c138a0445
commit 1466c1b896
1 changed files with 5 additions and 0 deletions
--- a/benchmark/kernels/fused_moe_triton/tuning_fused_moe_triton.py
+++ b/benchmark/kernels/fused_moe_triton/tuning_fused_moe_triton.py
@@ -427,6 +427,11 @@ def main(args: argparse.Namespace):
        topk = config.num_experts_per_tok
        intermediate_size = config.moe_intermediate_size
        shard_intermediate_size = 2 * intermediate_size // args.tp_size
+    elif config.architectures[0] in ["Glm4MoeForCausalLM"]:
+        E = config.n_routed_experts
+        topk = config.num_experts_per_tok
+        intermediate_size = config.moe_intermediate_size
+        shard_intermediate_size = 2 * intermediate_size // args.tp_size
    else:
        # Default: Mixtral
        E = config.num_local_experts