Add a meta-reference-quantized-gpu distribution

2025-06-27 18:50:41 +00:00 · 2024-10-23 19:33:14 -07:00 · 2024-10-23 19:33:14 -07:00 · 05a8d47b98
commit 05a8d47b98
parent f5dcc03742
6 changed files with 104 additions and 4 deletions
--- a/llama_stack/providers/registry/inference.py
+++ b/llama_stack/providers/registry/inference.py
@ -36,7 +36,7 @@ def available_providers() -> List[ProviderSpec]:
            pip_packages=(
                META_REFERENCE_DEPS
                + [
-                    "fbgemm-gpu==0.8.0",
+                    "fbgemm-gpu",
                ]
            ),
            module="llama_stack.providers.impls.meta_reference.inference",