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/modular_kernel_tools/profile_modular_kernel.py
View File

@@ -52,7 +52,7 @@ def profile_modular_kernel(
rank_weights = weights.slice_weights(pgi.rank, config.num_local_experts)
# make modular kernel
mk = make_modular_kernel(config, vllm_config)
mk = make_modular_kernel(config, vllm_config, weights)
mk_kwargs = {
"hidden_states": rank_tensors.hidden_states,
@@ -83,7 +83,7 @@ def rank_worker(
# sanity check
from vllm import envs
if config.fused_moe_chunk_size is not None:
assert (config.fused_moe_chunk_size == envs.VLLM_FUSED_MOE_CHUNK_SIZE)
assert config.fused_moe_chunk_size == envs.VLLM_FUSED_MOE_CHUNK_SIZE
# get weights to this device
weights.to_current_device()