AlpinDale ad24e74a99 feat: FP8 weight-only quantization support for Ampere GPUs 6 hónapja
..
aqlm 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 7 hónapja
autoquant 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 7 hónapja
awq 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 7 hónapja
compressed_tensors 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 7 hónapja
cutlass_w8a8 b03b4d4c8c fix: compute cutlass 3.x epilogues in fp32 instead of 16 7 hónapja
exl2 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 7 hónapja
fp8 ad24e74a99 feat: FP8 weight-only quantization support for Ampere GPUs 6 hónapja
gguf 9d81716bfd [v0.5.3] Release Candidate (#388) 10 hónapja
gptq 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 7 hónapja
gptq_marlin 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 7 hónapja
int8_kvcache 9810daa699 feat: INT8 KV Cache (#298) 1 éve
marlin 1587fab5de fix: cuda version check for mma warning suppression 7 hónapja
quip 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 7 hónapja
squeezellm 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 7 hónapja
quant_ops.h ad24e74a99 feat: FP8 weight-only quantization support for Ampere GPUs 6 hónapja