compressed-tensors GitHub README · inference-research

Fields

id

sources/qlab2-compressed-tensors-readme

URL

https://github.com/neuralmagic/compressed-tensors

Publisher

vLLM project / Red Hat AI

Kind

repo

Accessed

2026-10-03

notes

compressed-tensors is a safetensors extension. NOTE the repo has MOVED to the vllm-project org (GitHub redirects neuralmagic/ -> vllm-project/); the name is unchanged. Supports unstructured and semi-structured 2:4 sparsity, rotation-based quantization (Hadamard, random Hadamard, random matrix transforms), activation/KV-cache quantization, mixed precision, low/arbitrary-bit, non-uniform per-layer schemes, and checkpoint conversion from/to AutoAWQ, ModelOpt NVFP4, FP8 block. | SOURCE AUDIT 2026-10-03: the 'published' field held a verbatim copy of this notes paragraph instead of a date (field corruption across the qlab2-* batch); published set to null because a GitHub README, doc page or source header has no reliable publication date of its own. Content of the document itself was re-verified live 2026-10-03 and the notes are correct.

Notes

compressed-tensors is a safetensors extension. NOTE the repo has MOVED to the vllm-project org (GitHub redirects neuralmagic/ -> vllm-project/); the name is unchanged. Supports unstructured and semi-structured 2:4 sparsity, rotation-based quantization (Hadamard, random Hadamard, random matrix transforms), activation/KV-cache quantization, mixed precision, low/arbitrary-bit, non-uniform per-layer schemes, and checkpoint conversion from/to AutoAWQ, ModelOpt NVFP4, FP8 block. | SOURCE AUDIT 2026-10-03: the 'published' field held a verbatim copy of this notes paragraph instead of a date (field corruption across the qlab2-* batch); published set to null because a GitHub README, doc page or source header has no reliable publication date of its own. Content of the document itself was re-verified live 2026-10-03 and the notes are correct.

Cross-references

This record references no other records.