This website requires JavaScript.
Explore
Help
Sign In
xinyun
/
vllm
Watch
1
Star
0
Fork
0
You've already forked vllm
mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced
2026-04-16 05:37:03 +08:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
vllm
/
tests
/
kernels
/
moe
History
bnellnm
015fab8c2f
[Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward. Add additional testing for cudagraphs. (
#19717
)
...
Signed-off-by: Bill Nell <bnell@redhat.com>
2025-06-24 23:22:58 -07:00
..
__init__.py
…
deepep_utils.py
…
test_batched_moe.py
…
test_cutlass_moe.py
[Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward. Add additional testing for cudagraphs. (
#19717
)
2025-06-24 23:22:58 -07:00
test_deepep_deepgemm_moe.py
Revert "[Feature] Integrate new deepgemm (
#19820
)" (
#20049
)
2025-06-24 19:45:22 -07:00
test_deepep_moe.py
…
test_moe_align_block_size.py
…
test_moe_permute_unpermute.py
…
test_moe.py
[Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward. Add additional testing for cudagraphs. (
#19717
)
2025-06-24 23:22:58 -07:00
test_nvfp4_moe.py
[Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward. Add additional testing for cudagraphs. (
#19717
)
2025-06-24 23:22:58 -07:00
test_pplx_cutlass_moe.py
[Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward. Add additional testing for cudagraphs. (
#19717
)
2025-06-24 23:22:58 -07:00
test_pplx_moe.py
[Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward. Add additional testing for cudagraphs. (
#19717
)
2025-06-24 23:22:58 -07:00
test_rocm_aiter_topk.py
…
test_silu_mul_fp8_quant_deep_gemm.py
…
test_triton_moe_ptpc_fp8.py
…
