Skip to content

[Quantization] Refactor compressed-tensors quantization implement to reuse upstream implement. And add w4a16 support.#6644

Open
menogrey wants to merge 8 commits intovllm-project:mainfrom
menogrey:refactor_compressed_tensor
Open

[Quantization] Refactor compressed-tensors quantization implement to reuse upstream implement. And add w4a16 support.#6644
menogrey wants to merge 8 commits intovllm-project:mainfrom
menogrey:refactor_compressed_tensor

Commits

Commits on Mar 3, 2026