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
382970ee6ca490aeaaaf4e32c53695b581ff61ba
vLLM
/
csrc
/
libtorch_stable
/
quantization
/
w8a8
T
History
Thien Tran
and
Codex
8da75d6190
C3x SM100 FP8 blockwise - Pad activation scales to multiple of 4 (
#57377
)
...
Signed-off-by: Thien Tran <
gau.nernst@yahoo.com.sg
> Co-authored-by: Codex <
noreply@openai.com
>
2026-09-18 08:39:27 +00:00
..
cutlass
C3x SM100 FP8 blockwise - Pad activation scales to multiple of 4 (
#57377
)
2026-09-18 08:39:27 +00:00
fp8
[Kernel][Perf][Quantization] Fix odd-row performance cliff in per-token-group quantization (
#56478
)
2026-09-12 20:27:08 -07:00
int8
New stable abi cleanup (
#46656
)
2026-07-03 14:02:26 +08:00
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