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

[Misc] Fixes and Optimizations for DeepEP + DeepGEMM combination. (#19298)

Browse Source 
Signed-off-by: Varun <vsundarr@redhat.com>
Co-authored-by: Varun <vsundarr@redhat.com>
This commit is contained in:
Varun Sundar Rabindranath
2025-06-09 10:50:39 -04:00
committed by GitHub
parent b8089195b4
commit 5cf2daea9a
8 changed files with 98 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/kernels/moe/test_pplx_moe.py
View File

@@ -274,7 +274,7 @@ def pplx_prepare_finalize(pgi: ProcessGroupInfo, dp_size: int, a: torch.Tensor,
chunk_topk_weight = chunk_by_rank(topk_weight, rank, world_size).to(device)
chunk_topk_ids = chunk_by_rank(topk_ids, rank, world_size).to(device)
b_a, b_a_scale, expert_num_tokens = prepare_finalize.prepare(
b_a, b_a_scale, expert_num_tokens, _, _ = prepare_finalize.prepare(
a_chunk,
None,
None,