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

[Kernels] Clean up FusedMoeMethodBase and modular kernel setup. Remove extra arguments from modular kernel methods. (#22035)

Browse Source 
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
bnellnm
2025-08-15 14:46:00 -04:00
committed by GitHub
parent 48b01fd4d4
commit 8ad7285ea2
54 changed files with 2010 additions and 1293 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/kernels/moe/test_batched_moe.py
View File

@@ -133,7 +133,7 @@ def test_batched_mm(num_experts: int, max_tokens_per_expert: int, K: int,
per_act_token_quant=per_act_token_quant,
)
B, B_q, B_scale, _, _, _ = make_test_weights(
(B, B_q, B_scale, _), _ = make_test_weights(
num_experts,
N // 2,
K,
@@ -243,7 +243,7 @@ def test_fused_moe_batched_experts(
act_dtype = dtype
quant_dtype = None
w1_16, w1, w1_s, w2_16, w2, w2_s = make_test_weights(
(w1_16, w1, w1_s, _), (w2_16, w2, w2_s, _) = make_test_weights(
e,
n,
k,