| .. |
|
compressed_tensors
|
4d4e767838
ci: take one of fixing lint issues
|
4 달 전 |
|
gguf_utils
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 달 전 |
|
utils
|
141672a0d4
kernels: disambiguate quantized types via a new ScalarType
|
4 달 전 |
|
__init__.py
|
2b85ffb1a5
chore: minor cleanups
|
4 달 전 |
|
aqlm.py
|
9be43994fe
feat: fbgemm quantization support (#601)
|
5 달 전 |
|
autoquant.py
|
9be43994fe
feat: fbgemm quantization support (#601)
|
5 달 전 |
|
awq.py
|
9be43994fe
feat: fbgemm quantization support (#601)
|
5 달 전 |
|
awq_marlin.py
|
141672a0d4
kernels: disambiguate quantized types via a new ScalarType
|
4 달 전 |
|
base_config.py
|
0e6c400b13
feat: re-add GGUF (#600)
|
4 달 전 |
|
bitsandbytes.py
|
d4c9fcd6e6
feat: support loading pre-quanted bnb checkpoints
|
4 달 전 |
|
deepspeedfp.py
|
6b1fdd07bd
chore: add isort and refactor formatting script and utils
|
4 달 전 |
|
eetq.py
|
9be43994fe
feat: fbgemm quantization support (#601)
|
5 달 전 |
|
exl2.py
|
9be43994fe
feat: fbgemm quantization support (#601)
|
5 달 전 |
|
fbgemm_fp8.py
|
a20e2ce155
fix: pass cutlass_fp8_supported correctly for fbgemm_fp8
|
4 달 전 |
|
fp8.py
|
4d4e767838
ci: take one of fixing lint issues
|
4 달 전 |
|
gguf.py
|
4d4e767838
ci: take one of fixing lint issues
|
4 달 전 |
|
gptq.py
|
208cd5405f
fix: cpu offloading with gptq
|
4 달 전 |
|
gptq_marlin.py
|
208cd5405f
fix: cpu offloading with gptq
|
4 달 전 |
|
gptq_marlin_24.py
|
141672a0d4
kernels: disambiguate quantized types via a new ScalarType
|
4 달 전 |
|
hadamard.safetensors
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 달 전 |
|
kv_cache.py
|
e81590d293
fix: `kv_cache_dtype=fp8` without scales for fp8 checkpoints
|
4 달 전 |
|
marlin.py
|
9be43994fe
feat: fbgemm quantization support (#601)
|
5 달 전 |
|
qqq.py
|
e3f07b22c3
feat: support for QQQ W4A8 quantization (#612)
|
4 달 전 |
|
quip.py
|
9be43994fe
feat: fbgemm quantization support (#601)
|
5 달 전 |
|
quip_utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 달 전 |
|
schema.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 달 전 |
|
squeezellm.py
|
9be43994fe
feat: fbgemm quantization support (#601)
|
5 달 전 |
AlpinDale
208cd5405f
fix: cpu offloading with gptq