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

[GPTOSS][DP/EP][Marlin] Enable GPTOSS DP/EP using Marlin kernels (#25488)

Browse Source 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Varun Sundar Rabindranath
2025-10-03 20:13:13 -04:00
committed by GitHub
parent 767cbb011d
commit 7ef40bb983
9 changed files with 264 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/fused_moe/cutlass_moe.py
View File

@@ -712,7 +712,7 @@ class CutlassExpertsFp4(mk.FusedMoEPermuteExpertsUnpermute):
expert_tokens_meta: Optional[mk.ExpertTokensMetadata],
apply_router_weight_on_input: bool,
):
e, m, n, k, _ = mk._moe_problem_size(hidden_states, w1, w2, topk_ids)
e, m, n, k, _ = self.moe_problem_size(hidden_states, w1, w2, topk_ids)
n = w2.shape[2] * 2
run_cutlass_moe_fp4(