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
197473c4e71c99025a0fd3925d0f130bdbfa1e42
vllm
/
csrc
/
quantization
/
w8a8
History
czhu-cohere
f6227c22ab
[Kernel]Support W4A8 Grouped GEMM on Hopper (
#29691
)
...
Signed-off-by: czhu-cohere <
conway.zhu@cohere.com
>
2025-12-08 19:29:06 -08:00
..
cutlass
[Kernel]Support W4A8 Grouped GEMM on Hopper (
#29691
)
2025-12-08 19:29:06 -08:00
fp8
[Perf] Deepgemm fused layout kernel for activations, 4.3% throughput improvement, 10.7% TTFT improvement. (
#29546
)
2025-12-07 20:31:14 +08:00
int8
[Bugfix] Fix test fused quant layernorm tests (
#27865
)
2025-11-08 14:31:33 -08:00
per_token_group_quant_8bit.h
[Refactor] Refactor FP8 & INT8 Quant Folder inside
w8a8
(
#25293
)
2025-10-08 10:20:48 -04:00