A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 16:00 UTC
[Doc] Update rocm.inc.md (#15917)
Signed-off-by: chun37 <chun.jb.37@gmail.com>
chun committed
Apr 2, 2025 at 15:38 UTC
c920e01242c042d9d6143a306fcfb8b7adab9287
1 file changed
+1
-1
docs/source/getting_started/installation/gpu/rocm.inc.md
+1
-1
@@ -31,7 +31,7 @@ Currently, there are no pre-built ROCm wheels.
31
```console
32
# Install PyTorch
33
$ pip uninstall torch -y
34
- $ pip install --no-cache-dir --pre torch --index-url https://download.pytorch.org/whl/rocm6.3
34
+ $ pip install --no-cache-dir --pre torch --index-url https://download.pytorch.org/whl/nightly/rocm6.3
35
```
36
37
1. Install [Triton flash attention for ROCm](https://github.com/ROCm/triton)