| .. |
|
aqlm
|
705821a7fe
feat: AQLM quantization support (#293)
|
10 ヶ月 前 |
|
awq
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 ヶ月 前 |
|
bitsandbytes
|
a98babfb74
fix: bnb on Turing GPUs (#299)
|
10 ヶ月 前 |
|
exl2
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 ヶ月 前 |
|
fp8
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 ヶ月 前 |
|
fp8_e5m2_kvcache
|
8e1cd54497
fix: do not include fp8 for rocm (#271)
|
10 ヶ月 前 |
|
gguf
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 ヶ月 前 |
|
gptq
|
8cf8fa3f09
don't assign meta tensor to a cuda param
|
7 ヶ月 前 |
|
int8_kvcache
|
9810daa699
feat: INT8 KV Cache (#298)
|
10 ヶ月 前 |
|
marlin
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 ヶ月 前 |
|
quip
|
aebd68c632
feat: backport kernels (#235)
|
11 ヶ月 前 |
|
squeezellm
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
11 ヶ月 前 |
|
quant_ops.cpp
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 ヶ月 前 |
|
quant_ops.h
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 ヶ月 前 |
AlpinDale
8cf8fa3f09
don't assign meta tensor to a cuda param