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

[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375)

Browse Source 
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
This commit is contained in:
bnellnm
2026-02-05 13:07:18 -05:00
committed by GitHub
parent 1ee95841bd
commit a57c8228ff
37 changed files with 132 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/kernels/moe/test_block_fp8.py
View File

@@ -9,6 +9,7 @@ from tests.kernels.moe.utils import (
make_dummy_moe_config,
make_test_quant_config,
make_test_weights,
modular_triton_fused_moe,
)
from tests.kernels.quant_utils import (
native_per_token_group_quant_fp8,
@@ -26,9 +27,6 @@ from vllm.model_executor.layers.fused_moe.config import (
from vllm.model_executor.layers.fused_moe.deep_gemm_moe import (
_valid_deep_gemm_shape,
)
from vllm.model_executor.layers.fused_moe.fused_moe import (
modular_triton_fused_moe,
)
from vllm.model_executor.layers.fused_moe.prepare_finalize import (
MoEPrepareAndFinalizeNoEP,
)
@@ -261,6 +259,7 @@ def test_w8a8_block_fp8_deep_gemm_fused_moe(M, N, K, E, topk, seed, monkeypatch)
moe_config=make_dummy_moe_config(),
quant_config=quant_config,
),
inplace=False,
)
def deep_gemm_moe_fp8(a, w1, w2, w1_s, w2_s, topk_weights, topk_ids):