Skip to content

Commit 18a2516

Browse files
Update docs/advanced/environment-variables.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
1 parent 5966115 commit 18a2516

1 file changed

Lines changed: 1 addition & 1 deletion

File tree

docs/advanced/environment-variables.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -151,7 +151,7 @@ For Windows ROCm-based WebUI package launches, Stability Matrix already applies
151151
| `MIOPEN_SEARCH_CUTOFF` | `1` | |
152152
| `MIOPEN_FIND_ENFORCE` | `1` | |
153153
| `TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL` | `1` | Enables the experimental ROCm AOTriton path. Applied only on RDNA3 / RDNA3.5 / RDNA4 GPUs, and additionally excluded on gfx1152/gfx1153 APU architectures where AOTriton isn't yet supported. |
154-
| `FLASH_ATTENTION_TRITON_AMD_ENABLE` | `TRUE` | Enables the Triton-based Flash Attention implementation for AMD GPUs, providing an efficient attention path when the native ROCm Flash Attention is unavailable and instead provided by a seperate FA python package. |
154+
| `FLASH_ATTENTION_TRITON_AMD_ENABLE` | `TRUE` | Enables the Triton-based Flash Attention implementation for AMD GPUs, providing an efficient attention path when the native ROCm Flash Attention is unavailable and instead provided by a separate FA Python package. |
155155
| `COMFYUI_ENABLE_MIOPEN` | `1` | Keeps the MIOpen-backed path enabled in ComfyUI on RDNA3 / RDNA3.5 / RDNA4 GPUs. |
156156
| `PYTORCH_ALLOC_CONF` | `max_split_size_mb:512,garbage_collection_threshold:0.8` | |
157157

0 commit comments

Comments
 (0)