This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
cd347298e86c83d43d3d404b05899b1be07489d1
vLLM
/
csrc
/
libtorch_stable
/
quantization
/
w8a8
T
History
Cyrus Leung
24d5186138
[Bugfix] Re-enable FP8 MoE on NVIDIA Thor (
#46339
)
...
Signed-off-by: DarkLight1337 <
tlleungac@connect.ust.hk
>
2026-06-24 07:35:46 -07:00
..
cutlass
[Bugfix] Re-enable FP8 MoE on NVIDIA Thor (
#46339
)
2026-06-24 07:35:46 -07:00
fp8
[Bugfix] Fix gridDim.y overflow for large row counts (
#45255
)
2026-06-19 23:27:45 -04:00
int8
[6/n] Migrate activation kernels, gptq, gguf, non cutlass w8a8 to libtorch stable ABI (continued) (
#42663
)
2026-05-20 00:18:12 -07:00
per_token_group_quant_8bit.h
Faster per-token fp8 group quant packed kernel for blackwell (
#41326
)
2026-04-30 18:09:55 -07:00