a785000842
compressed-tensors is a safetensors extension for sparse, quantized tensors. The format is more powerful than earlier AWQ/GPTQ/FP8 quantization, because - Different quantizer configurations can be used for different targets. - The format can specify input/output quantizers in addition to weight quantizers. - Configurable exclusions for quantization. This change adds a dependency on the `compressed-tensors` package for its configuration parsing and layer matching functionality. The following types of quantization are supported in this PR: - W8A16 and W4A16 INT using GPTQ-Marlin kernels. - W8A8 and W8A16 FP using FP8-Marlin and cutlass kernels. Support for other quantization types will be added in subsequent PRs. |
||
|---|---|---|
| .. | ||
| basic_tutorials | ||
| conceptual | ||
| reference | ||
| _toctree.yml | ||
| architecture.md | ||
| index.md | ||
| installation.md | ||
| installation_amd.md | ||
| installation_gaudi.md | ||
| installation_inferentia.md | ||
| installation_intel.md | ||
| installation_nvidia.md | ||
| quicktour.md | ||
| supported_models.md | ||
| usage_statistics.md | ||