vLLM/vllm/model_executor/layers/quantization/quark at 36fa72d2d0d2f86c7c83e1e99c9012b7bd26463b - vLLM - iHore Software Repository

iHore/vLLM

Files

T

History

meng-amd 6df2b1a8c6 [Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM (#48606 )

Signed-off-by: HongWei Meng <HongWei.Meng@amd.com>

2026-09-18 17:52:46 +08:00

..

[Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM (#48606 )

2026-09-18 17:52:46 +08:00

__init__.py

[Misc][Quark] Upstream Quark format to VLLM (#10765 )

2025-01-15 11:05:15 -05:00

quark_moe.py

[Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM (#48606 )

2026-09-18 17:52:46 +08:00

quark.py

[Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM (#48606 )

2026-09-18 17:52:46 +08:00

utils.py

[Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM (#48606 )

2026-09-18 17:52:46 +08:00