allow changing model parallel size

llama_stack/templates/dependencies.json

@@ -356,50 +356,7 @@
     "fairscale",
     "faiss-cpu",
     "fastapi",
-    "fire",
-    "httpx",
-    "langdetect",
-    "lm-format-enforcer",
-    "matplotlib",
-    "mcp",
-    "nltk",
-    "numpy",
-    "openai",
-    "opentelemetry-exporter-otlp-proto-http",
-    "opentelemetry-sdk",
-    "pandas",
-    "pillow",
-    "psycopg2-binary",
-    "pymongo",
-    "pypdf",
-    "pythainlp",
-    "redis",
-    "requests",
-    "scikit-learn",
-    "scipy",
-    "sentence-transformers",
-    "sentencepiece",
-    "torch",
-    "torchvision",
-    "tqdm",
-    "transformers",
-    "tree_sitter",
-    "uvicorn",
-    "zmq"
-  ],
-  "meta-reference-quantized-gpu": [
-    "accelerate",
-    "aiosqlite",
-    "autoevals",
-    "blobfile",
-    "chardet",
-    "chromadb-client",
-    "datasets",
-    "emoji",
-    "fairscale",
-    "faiss-cpu",
-    "fastapi",
-    "fbgemm-gpu",
+    "fbgemm-gpu-genai==1.1.2",
     "fire",
     "httpx",
     "langdetect",