| .. |
|
aqlm
|
ccbda97416
fix: types in AQLM and GGUF for dynamo support (#736)
|
6 месяцев назад |
|
autoquant
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 месяцев назад |
|
awq
|
064c701d18
formatting
|
4 месяцев назад |
|
compressed_tensors
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 месяцев назад |
|
cutlass_w8a8
|
a401f8e05d
feat: per-tensor token epilogue kernels (#630)
|
6 месяцев назад |
|
exl2
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 месяцев назад |
|
fp6
|
73177656ed
feat: quant_llm support (#755)
|
6 месяцев назад |
|
fp8
|
064c701d18
formatting
|
4 месяцев назад |
|
gguf
|
ccbda97416
fix: types in AQLM and GGUF for dynamo support (#736)
|
6 месяцев назад |
|
gptq
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 месяцев назад |
|
gptq_marlin
|
064c701d18
formatting
|
4 месяцев назад |
|
int8_kvcache
|
9810daa699
feat: INT8 KV Cache (#298)
|
1 год назад |
|
marlin
|
378d624b3d
initial support; port most of the kernels
|
5 месяцев назад |
|
quip
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 месяцев назад |
|
squeezellm
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 месяцев назад |
|
quant_ops.h
|
064c701d18
formatting
|
4 месяцев назад |
AlpinDale
064c701d18
formatting