[ROCm] Fixes for GPTQ on ROCm (#2180)

This commit is contained in:
kliuae
2023-12-19 02:41:04 +08:00
committed by GitHub
parent bbe4466fd9
commit 1b7c791d60
4 changed files with 23 additions and 16 deletions

View File

@@ -116,6 +116,7 @@ Alternatively, if you plan to install vLLM-ROCm on a local machine or start from
- `ROCm <https://rocm.docs.amd.com/en/latest/deploy/linux/index.html>`_
- `Pytorch <https://pytorch.org/>`_
- `hipBLAS <https://rocm.docs.amd.com/projects/hipBLAS/en/latest/install.html>`_
1. Install `flash attention for ROCm <https://github.com/ROCmSoftwarePlatform/flash-attention/tree/flash_attention_for_rocm>`_