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
2026-03-20 03:34:28 +08:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
vllm
/
benchmarks
/
kernels
History
Cyrus Leung
6c117cff7d
[Frontend] Pass API server count to each process (
#23717
)
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-09-20 01:15:19 +08:00
..
deepgemm
…
bench_block_fp8_gemm.py
[Perf] Use upstream CUTLASS for SM90 Block FP8 kernel (
#23280
)
2025-09-11 15:43:14 -07:00
bench_fp8_gemm.py
…
bench_int8_gemm.py
…
bench_nvfp4_gemm.py
…
bench_per_token_quant_fp8.py
[FP8] Extend per-token-group quantization support to QuantFP8 (
#24342
)
2025-09-16 18:31:06 -07:00
benchmark_activation.py
…
benchmark_bitblas.py
…
benchmark_cutlass_fp4_moe.py
[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (
#22537
)
2025-09-17 17:43:31 -06:00
benchmark_device_communicators.py
[Kernels] Enable Torch Symmetric Memory All-Reduce By Default (
#24111
)
2025-09-11 09:45:31 -07:00
benchmark_grouped_gemm_cutlass.py
[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (
#22537
)
2025-09-17 17:43:31 -06:00
benchmark_layernorm.py
…
benchmark_lora.py
[fix] lora benchmarks pass no_lora_flag_cpu (
#23774
)
2025-09-17 21:22:25 +08:00
benchmark_machete.py
…
benchmark_marlin.py
…
benchmark_moe_align_block_size.py
…
benchmark_moe_permute_unpermute.py
…
benchmark_moe.py
[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (
#22537
)
2025-09-17 17:43:31 -06:00
benchmark_mrope.py
…
benchmark_paged_attention.py
…
benchmark_per_token_group_quant.py
…
benchmark_polynorm.py
…
benchmark_quant.py
…
benchmark_reshape_and_cache_flash.py
…
benchmark_rmsnorm.py
…
benchmark_rope.py
…
benchmark_shapes.py
…
benchmark_silu_mul_fp8_quant.py
[Kernels][DP/EP] Optimize Silu Kernel for R1 (
#24054
)
2025-09-13 00:17:27 -07:00
benchmark_trtllm_decode_attention.py
…
benchmark_trtllm_prefill_attention.py
…
benchmark_w8a8_block_fp8.py
[Frontend] Pass API server count to each process (
#23717
)
2025-09-20 01:15:19 +08:00
graph_machete_bench.py
…
requirements.txt
…
utils.py
…
weight_shapes.py
…