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