| .. |
|
aqlm
|
705821a7fe
feat: AQLM quantization support (#293)
|
10 달 전 |
|
awq
|
5053743c1c
feat: speedup AWQ (#223)
|
11 달 전 |
|
bitsandbytes
|
a98babfb74
fix: bnb on Turing GPUs (#299)
|
10 달 전 |
|
exl2
|
c41462cfcd
feat: exllamav2 quantization (#305)
|
10 달 전 |
|
fp8_e5m2_kvcache
|
8e1cd54497
fix: do not include fp8 for rocm (#271)
|
10 달 전 |
|
gguf
|
c3a221eb02
feat: GGUF, QuIP#, and Marlin support (#228)
|
11 달 전 |
|
gptq
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
11 달 전 |
|
int8_kvcache
|
9810daa699
feat: INT8 KV Cache (#298)
|
10 달 전 |
|
marlin
|
72229a94da
feat: better marlin kernels (#285)
|
10 달 전 |
|
quip
|
aebd68c632
feat: backport kernels (#235)
|
11 달 전 |
|
squeezellm
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
11 달 전 |
AlpinDale
c41462cfcd
feat: exllamav2 quantization (#305)