.. |
aqlm
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 mēneši atpakaļ |
autoquant
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 mēneši atpakaļ |
awq
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 mēneši atpakaļ |
compressed_tensors
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 mēneši atpakaļ |
cutlass_w8a8
|
5b464d36ea
feat: bias epilogue support for cutlass kernels
|
7 mēneši atpakaļ |
exl2
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 mēneši atpakaļ |
fp8
|
37c6da9eb3
feat: vectorized fp8 quant kernel
|
7 mēneši atpakaļ |
gguf
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 mēneši atpakaļ |
gptq
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 mēneši atpakaļ |
gptq_marlin
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 mēneši atpakaļ |
int8_kvcache
|
9810daa699
feat: INT8 KV Cache (#298)
|
1 gadu atpakaļ |
marlin
|
1587fab5de
fix: cuda version check for mma warning suppression
|
7 mēneši atpakaļ |
quip
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 mēneši atpakaļ |
squeezellm
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 mēneši atpakaļ |
quant_ops.h
|
5b464d36ea
feat: bias epilogue support for cutlass kernels
|
7 mēneši atpakaļ |