| .. |
|
compressed_tensors
|
e2dbe5f05c
feat: add sparse marlin for compressed tensors
|
7 月之前 |
|
gguf_utils
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 月之前 |
|
__init__.py
|
517676249c
chore: update the compressed-tensors config
|
7 月之前 |
|
aqlm.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
autoquant.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
awq.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
base_config.py
|
c66b1b57b1
Marlin 2:4 sparsity (#555)
|
7 月之前 |
|
bitsandbytes.py
|
690110a051
feat: bitsandbytes quantization
|
7 月之前 |
|
deepspeedfp.py
|
4acf34417a
feat: add DeepSpeedFP quantization for all models
|
7 月之前 |
|
eetq.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 月之前 |
|
exl2.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
fp8.py
|
7e54c3916d
chore: factor out epilogues from cutlass kernels
|
7 月之前 |
|
gguf.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
gptq.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
gptq_marlin.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
gptq_marlin_24.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
hadamard.safetensors
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 月之前 |
|
marlin.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
quip.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
quip_utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 月之前 |
|
schema.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 月之前 |
|
squeezellm.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
AlpinDale
e2dbe5f05c
feat: add sparse marlin for compressed tensors