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

[Feature]: Remove Chunking From FusedMoE (#34086)

Browse Source 
Signed-off-by: SouthWest7 <am1ao@qq.com>
Signed-off-by: Southwest <1403572259@qq.com>
Signed-off-by: southwest <am1ao@qq.com>
Signed-off-by: Xinan Miao <1403572259@qq.com>
Co-authored-by: SouthWest7 <am1ao@qq.com>
This commit is contained in:
Xinan Miao
2026-03-13 02:24:38 +08:00
committed by GitHub
parent c973ecdead
commit 2cdf92228c
28 changed files with 152 additions and 523 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -321,7 +321,6 @@ def test_cutlass_moe_8_bit_no_graph(
ep_size: int | None = None,
):
set_random_seed(7)
monkeypatch.setenv("VLLM_FUSED_MOE_CHUNK_SIZE", "8192")
with set_current_vllm_config(vllm_config):
mt = MOETensors8Bit.make_moe_tensors_8bit(m, k, n, e, per_act_token, per_out_ch)
@@ -376,7 +375,6 @@ def test_cutlass_moe_8_bit_cuda_graph(
workspace_init,
):
set_random_seed(7)
monkeypatch.setenv("VLLM_FUSED_MOE_CHUNK_SIZE", "8192")
with set_current_vllm_config(vllm_config):
dtype = torch.half