This website requires JavaScript.
Explore
Help
Sign In
karylab_agents
/
vllm
Watch
1
Star
0
Fork
0
forked from
Karylab-cklius/vllm
Code
Pull Requests
2
Actions
1
Packages
Activity
Files
02a7fabdcaabc28f20735e2de4b8bc2eff621786
vllm
/
csrc
/
quantization
/
fused_kernels
T
History
Luka Govedič
02a7fabdca
Add support for non-contiguous input for rms-quant (dynamic & block)
...
Signed-off-by: Luka Govedič <
lgovedic@redhat.com
>
2026-03-10 11:53:56 -04:00
..
fused_layernorm_dynamic_per_token_quant.cu
Add support for non-contiguous input for rms-quant (dynamic & block)
2026-03-10 11:53:56 -04:00
layernorm_utils.cuh
Add support for non-contiguous input for rms-quant (dynamic & block)
2026-03-10 11:53:56 -04:00
quant_conversions.cuh
[Refactor] Refactor FP8 & INT8 Quant Folder inside
w8a8
(
#25293
)
2025-10-08 10:20:48 -04:00
