From 40d70864e710abd465be23fbc4a10252bde8b70e Mon Sep 17 00:00:00 2001
From: Dinesh Yeduguru <yvdinesh@gmail.com>
Date: Fri, 13 Dec 2024 09:32:42 -0800
Subject: [PATCH] do not mention  sentence transformer provider in docs

---
 distributions/dependencies.json               | 40 +++++++++++++++++++
 .../meta-reference-quantized-gpu.md           |  2 +-
 .../meta-reference-quantized-gpu/build.yaml   |  1 -
 .../meta_reference.py                         |  5 +--
 4 files changed, 42 insertions(+), 6 deletions(-)

diff --git a/distributions/dependencies.json b/distributions/dependencies.json
index 08595e479..7a974b917 100644
--- a/distributions/dependencies.json
+++ b/distributions/dependencies.json
@@ -260,6 +260,46 @@
     "sentence-transformers --no-deps",
     "torch --index-url https://download.pytorch.org/whl/cpu"
   ],
+  "meta-reference-quantized-gpu": [
+    "accelerate",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "fairscale",
+    "faiss-cpu",
+    "fastapi",
+    "fbgemm-gpu",
+    "fire",
+    "httpx",
+    "lm-format-enforcer",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pypdf",
+    "redis",
+    "scikit-learn",
+    "scipy",
+    "sentence-transformers",
+    "sentencepiece",
+    "torch",
+    "torchao==0.5.0",
+    "torchvision",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "zmq",
+    "sentence-transformers --no-deps",
+    "torch --index-url https://download.pytorch.org/whl/cpu"
+  ],
   "cerebras": [
     "aiosqlite",
     "blobfile",
diff --git a/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md b/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md
index 89e62657c..837be744a 100644
--- a/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md
+++ b/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md
@@ -17,7 +17,7 @@ The `llamastack/distribution-meta-reference-quantized-gpu` distribution consists
 | agents | `inline::meta-reference` |
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
-| inference | `inline::meta-reference-quantized`, `remote::sentence-transformers` |
+| inference | `inline::meta-reference-quantized` |
 | memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
diff --git a/llama_stack/templates/meta-reference-quantized-gpu/build.yaml b/llama_stack/templates/meta-reference-quantized-gpu/build.yaml
index d81744900..9d866de18 100644
--- a/llama_stack/templates/meta-reference-quantized-gpu/build.yaml
+++ b/llama_stack/templates/meta-reference-quantized-gpu/build.yaml
@@ -6,7 +6,6 @@ distribution_spec:
   providers:
     inference:
     - inline::meta-reference-quantized
-    - remote::sentence-transformers
     memory:
     - inline::faiss
     - remote::chromadb
diff --git a/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py b/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
index f1a1f90cd..c460860c5 100644
--- a/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
+++ b/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
@@ -21,10 +21,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 
 def get_distribution_template() -> DistributionTemplate:
     providers = {
-        "inference": [
-            "inline::meta-reference-quantized",
-            "remote::sentence-transformers",
-        ],
+        "inference": ["inline::meta-reference-quantized"],
         "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],