Files
LocalAI/backend/python/fish-speech
Ettore Di Giacinto f5ea6e4eab fix(fish-speech): use CUDA toolkit ptxas
Prefer an explicitly configured Triton assembler, otherwise use the executable ptxas from CUDA_HOME so torch.compile can target GPU architectures newer than Triton bundled tooling.

Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-09-11 21:48:54 +00:00
..
2026-03-12 07:48:23 +01:00