biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc]: fixing typos to improve docs (#24480)

Browse Source 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
This commit is contained in:
Didier Durand
2025-09-09 08:06:04 +02:00
committed by GitHub
parent 1823a00d67
commit 46876dff32
9 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/getting_started/installation/gpu/rocm.inc.md
View File

@@ -119,7 +119,7 @@ Currently, there are no pre-built ROCm wheels.
This may take 5-10 minutes. Currently, `pip install .` does not work for ROCm installation.
!!! tip
- Triton flash attention is used by default. For benchmarking purposes, it is recommended to run a warm up step before collecting perf numbers.
- Triton flash attention is used by default. For benchmarking purposes, it is recommended to run a warm-up step before collecting perf numbers.
- Triton flash attention does not currently support sliding window attention. If using half precision, please use CK flash-attention for sliding window support.
- To use CK flash-attention or PyTorch naive attention, please use this flag `export VLLM_USE_TRITON_FLASH_ATTN=0` to turn off triton flash attention.
- The ROCm version of PyTorch, ideally, should match the ROCm driver version.