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