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
cc06b4e86b2beb04fbee3e6d9167cc97f1491b1f
vllm
/
csrc
/
moe
/
marlin_moe_wna16
History
IriKa
148a5c1226
[Bugfix]fix output Nan/Inf in marlin if dtype=float16 (
#33972
)
...
Signed-off-by: IriKa Qiu <
qiujie.jq@gmail.com
>
2026-03-27 16:36:08 -07:00
..
.gitignore
[Kernel][Quantization][MoE] add marlin kernel support for turing (sm75) (
#29901
)
2025-12-16 14:35:28 -08:00
generate_kernels.py
Add thread_n=64 support to Marlin MoE (
#32360
)
2026-01-15 16:45:44 -08:00
kernel.h
[Bugfix]fix output Nan/Inf in marlin if dtype=float16 (
#33972
)
2026-03-27 16:36:08 -07:00
marlin_template.h
[Bugfix]fix output Nan/Inf in marlin if dtype=float16 (
#33972
)
2026-03-27 16:36:08 -07:00
ops.cu
[Bugfix]fix output Nan/Inf in marlin if dtype=float16 (
#33972
)
2026-03-27 16:36:08 -07:00