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
e30cedd44be332e1ddc7ec43b8a33bce532e7614
vllm
/
benchmarks
/
kernels
History
Mohammad Miadh Angkad
d4f123cc48
[Kernel] FlashInfer: switch allreduce fusion to unified API (
#33985
)
...
Signed-off-by: Mohammad Miadh Angkad <
176301910+mmangkad@users.noreply.github.com
>
2026-02-09 15:43:24 +00:00
..
cpu
…
deepgemm
…
bench_block_fp8_gemm.py
…
bench_fp8_gemm.py
…
bench_int8_gemm.py
…
bench_mxfp4_qutlass.py
…
bench_nvfp4_gemm.py
…
bench_nvfp4_quant.py
…
bench_nvfp4_qutlass.py
…
bench_per_token_quant_fp8.py
…
benchmark_2d_silu_mul_fp8_quant.py
…
benchmark_activation.py
…
benchmark_cutlass_moe_fp8.py
…
benchmark_cutlass_moe_nvfp4.py
…
benchmark_device_communicators.py
…
benchmark_fused_collective.py
[Kernel] FlashInfer: switch allreduce fusion to unified API (
#33985
)
2026-02-09 15:43:24 +00:00
benchmark_fused_topk.py
…
benchmark_grouped_gemm_cutlass.py
…
benchmark_layernorm.py
…
benchmark_lora.py
…
benchmark_machete.py
…
benchmark_marlin.py
…
benchmark_mla_k_concat.py
…
benchmark_moe_align_block_size.py
…
benchmark_moe_permute_unpermute.py
[Refactor] Remove align block size logic in
moe_permute
(
#33449
)
2026-02-06 10:57:06 -08:00
benchmark_moe.py
[Model] GLM adaptation (
#34124
)
2026-02-09 17:32:52 +08:00
benchmark_mrope.py
…
benchmark_paged_attention.py
…
benchmark_per_token_group_quant.py
…
benchmark_quant.py
…
benchmark_reshape_and_cache_flash.py
…
benchmark_reshape_and_cache.py
…
benchmark_rmsnorm.py
…
benchmark_rope.py
…
benchmark_shapes.py
…
benchmark_silu_mul_fp8_quant.py
…
benchmark_trtllm_decode_attention.py
…
benchmark_trtllm_prefill_attention.py
…
benchmark_w8a8_block_fp8.py
…
graph_machete_bench.py
…
requirements.txt
…
utils.py
…
weight_shapes.py
…