use experimental features; runtime fix

This commit is contained in:
Dobromir Popov
2025-11-22 23:17:10 +02:00
parent f38a924b0f
commit 3eb74381a8
6 changed files with 263 additions and 38 deletions

View File

@@ -84,7 +84,8 @@ The environment variable has been automatically added to your venv activation sc
### What was done:
1. Added `export HSA_OVERRIDE_GFX_VERSION=11.0.0` to `venv/bin/activate`
2. This allows gfx1151 to use gfx1100 libraries (fully compatible)
3. All PyTorch operations now work on GPU
3. Added `export TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1` for Flash Efficient attention
4. All PyTorch operations now work on GPU with experimental optimizations
### To apply:
```bash