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

[Kernel] Enable fp8 support for pplx and BatchedTritonExperts. (#18864)

Browse Source 
Signed-off-by: Bill Nell <bnell@redhat.com>
This commit is contained in:
bnellnm
2025-07-03 17:55:40 -04:00
committed by GitHub
parent 2f2fcb31b8
commit 78fe77534b
25 changed files with 1277 additions and 663 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/kernels/moe/test_deepep_deepgemm_moe.py
View File

@@ -148,8 +148,7 @@ def make_ll_modular_kernel(pg: ProcessGroup, pgi: ProcessGroupInfo,
fused_experts = BatchedDeepGemmExperts(
max_num_tokens=max_tokens_per_rank,
world_size=pgi.world_size,
dp_size=dp_size,
num_dispatchers=pgi.world_size // dp_size,
block_shape=test_config.block_size,
per_act_token_quant=test_config.per_act_token_quant)
mk = FusedMoEModularKernel(prepare_finalize=a2a,