AlpinDale 04da8c33bd Revert "chore: use the `compressed-tensors` library to avoid code reuse (#704)" (#706) 4 ヶ月 前
..
compressed_tensors 04da8c33bd Revert "chore: use the `compressed-tensors` library to avoid code reuse (#704)" (#706) 4 ヶ月 前
gguf_utils 9d81716bfd [v0.5.3] Release Candidate (#388) 8 ヶ月 前
utils 3170c0d4c6 fix: GPTQ/AWQ on Colab (#655) 4 ヶ月 前
__init__.py 3f49a55f82 feat: add INT8 W8A16 quant for TPU (#663) 4 ヶ月 前
aqlm.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
autoquant.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
awq.py edec2e9a9e feat: migrate awq and awq_marlin to AphroditeParameter (#702) 4 ヶ月 前
awq_marlin.py edec2e9a9e feat: migrate awq and awq_marlin to AphroditeParameter (#702) 4 ヶ月 前
base_config.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
bitsandbytes.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
deepspeedfp.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
eetq.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
exl2.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
fbgemm_fp8.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
fp8.py 4ec08af18b chore: update fused MoE weight loading (#700) 4 ヶ月 前
gguf.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
gptq.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
gptq_marlin.py 4f6020cc86 chore: migrate gptq_marlin to AphroditeParameters (#699) 4 ヶ月 前
gptq_marlin_24.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
hadamard.safetensors 9d81716bfd [v0.5.3] Release Candidate (#388) 8 ヶ月 前
kv_cache.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
marlin.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
qqq.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
quip.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
quip_utils.py 9d81716bfd [v0.5.3] Release Candidate (#388) 8 ヶ月 前
schema.py 9d81716bfd [v0.5.3] Release Candidate (#388) 8 ヶ月 前
squeezellm.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 ヶ月 前
tpu_int8.py 3f49a55f82 feat: add INT8 W8A16 quant for TPU (#663) 4 ヶ月 前