This website requires JavaScript.
Explore
Help
Register
Sign In
biondizzle
/
vllm
Watch
1
Star
0
Fork
0
You've already forked vllm
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
9df152bbf6c27db737636960ae791546d65269fc
vllm
/
csrc
/
moe
History
Wentao Ye
c4e744dbd4
[Perf] Optimize
moe_permute
for CUTLASS FP8 (
#32892
)
...
Signed-off-by: yewentao256 <
zhyanwentao@126.com
>
2026-01-28 10:15:24 -08:00
..
marlin_moe_wna16
[Refactor] Rename
gptq_marlin
to
marlin
to match MoE (
#32952
)
2026-01-23 16:48:12 -05:00
permute_unpermute_kernels
[Perf] Optimize
moe_permute
for CUTLASS FP8 (
#32892
)
2026-01-28 10:15:24 -08:00
dynamic_4bit_int_moe_cpu.cpp
…
grouped_topk_kernels.cu
[Perf] Optimize grouped topk kernel, 1.2%~2% E2E Throughput improvement (
#32058
)
2026-01-13 10:58:18 -08:00
moe_align_sum_kernels.cu
…
moe_ops.h
[Kernel] Add topk_sigmoid kernel (
#31246
)
2026-01-21 22:49:51 +00:00
moe_permute_unpermute_op.cu
[Perf] Optimize
moe_permute
for CUTLASS FP8 (
#32892
)
2026-01-28 10:15:24 -08:00
moe_wna16_utils.h
…
moe_wna16.cu
…
topk_softmax_kernels.cu
[Kernel] Add topk_sigmoid kernel (
#31246
)
2026-01-21 22:49:51 +00:00
torch_bindings.cpp
[Kernel] Add topk_sigmoid kernel (
#31246
)
2026-01-21 22:49:51 +00:00
