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, 21:00 UTC
[Doc] Fix ROCm documentation (#14041)
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Brayden Zhong committed
Feb 28, 2025 at 11:42 UTC
2aed2c9fa7f9f751b994c6563893dcb048e0ae7b
1 file changed
+2
-2
docs/source/getting_started/installation/gpu/rocm.inc.md
+2
-2
@@ -53,9 +53,9 @@ Currently, there are no pre-built ROCm wheels.
53
If you see HTTP issue related to downloading packages during building triton, please try again as the HTTP error is intermittent.
54
:::
55
56
-2. Optionally, if you choose to use CK flash attention, you can install [flash attention for ROCm](https://github.com/ROCm/flash-attention/tree/ck_tile)
56
+2. Optionally, if you choose to use CK flash attention, you can install [flash attention for ROCm](https://github.com/ROCm/flash-attention)
57
58
- Install ROCm's flash attention (v2.7.2) following the instructions from [ROCm/flash-attention](https://github.com/ROCm/flash-attention/tree/ck_tile#amd-gpurocm-support)
58
+ Install ROCm's flash attention (v2.7.2) following the instructions from [ROCm/flash-attention](https://github.com/ROCm/flash-attention#amd-rocm-support)
59
Alternatively, wheels intended for vLLM use can be accessed under the releases.
60
61
For example, for ROCm 6.3, suppose your gfx arch is `gfx90a`. To get your gfx architecture, run `rocminfo |grep gfx`.