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
2026-03-24 00:35:51 +08:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
vllm
/
tests
/
kernels
History
Jinzhen Lin
1d0c9d6b2d
[Kernel] some optimizations for dense marlin and moe marlin (
#16850
)
...
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
2025-05-05 09:39:30 -07:00
..
attention
Update test_flash_attn.py (
#17102
)
2025-04-26 22:17:35 +00:00
core
…
mamba
…
moe
[Kernel] some optimizations for dense marlin and moe marlin (
#16850
)
2025-05-05 09:39:30 -07:00
quantization
[Kernel] some optimizations for dense marlin and moe marlin (
#16850
)
2025-05-05 09:39:30 -07:00
__init__.py
…
allclose_default.py
…
quant_utils.py
Add missing rocm_skinny_gemms kernel test to CI (
#17060
)
2025-04-24 07:49:37 -07:00
test_cutlass_mla_decode.py
[NVIDIA] Support Cutlass MLA for Blackwell GPUs (
#16032
)
2025-04-27 06:29:21 -07:00
test_fused_quant_activation.py
[torch.compile] Add torch inductor pass for fusing silu_and_mul with subsequent scaled_fp8_quant operations (
#10867
)
2025-05-01 07:59:28 -07:00
test_triton_flash_attention.py
[Kernel][Triton][FP8] Adding fp8 and variable length sequence support to Triton FAv2 kernel (
#12591
)
2025-04-27 00:35:08 +00:00
utils.py
…
