LM Studio inference integration

Co-authored-by: Rugved Somwanshi <rugved@lmstudio.ai>
2025-12-29 16:44:43 +00:00 · 2025-03-14 15:21:15 -04:00 · 2025-03-14 15:21:15 -04:00 · 461eec425d
commit 461eec425d
parent 1bb1d9b2ba
16 changed files with 1096 additions and 0 deletions
--- a/llama_stack/templates/dependencies.json
+++ b/llama_stack/templates/dependencies.json
@ -344,6 +344,38 @@
    "sentence-transformers --no-deps",
    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
  ],
+  "lmstudio": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "lmstudio",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "uvicorn"
+  ],
  "meta-reference-gpu": [
    "accelerate",
    "aiosqlite",
--- a/llama_stack/templates/lmstudio/init.py
+++ b/llama_stack/templates/lmstudio/init.py
@ -0,0 +1,7 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from .lmstudio import get_distribution_template  # noqa: F401
--- a/llama_stack/templates/lmstudio/build.yaml
+++ b/llama_stack/templates/lmstudio/build.yaml
@ -0,0 +1,31 @@
+version: '2'
+distribution_spec:
+  description: Use LM Studio for running LLM inference
+  providers:
+    inference:
+    - remote::lmstudio
+    safety:
+    - inline::llama-guard
+    vector_io:
+    - inline::faiss
+    - remote::chromadb
+    - remote::pgvector
+    agents:
+    - inline::meta-reference
+    eval:
+    - inline::meta-reference
+    datasetio:
+    - remote::huggingface
+    - inline::localfs
+    scoring:
+    - inline::basic
+    - inline::llm-as-judge
+    - inline::braintrust
+    telemetry:
+    - inline::meta-reference
+    tool_runtime:
+    - remote::brave-search
+    - remote::tavily-search
+    - inline::code-interpreter
+    - inline::rag-runtime
+image_type: conda
--- a/llama_stack/templates/lmstudio/doc_template.md
+++ b/llama_stack/templates/lmstudio/doc_template.md
@ -0,0 +1,58 @@
+# LM Studio Distribution
+
+The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
+
+{{ providers_table }}
+
+{% if run_config_env_vars %}
+### Environment Variables
+
+The following environment variables can be configured:
+
+{% for var, (default_value, description) in run_config_env_vars.items() %}
+- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
+{% endfor %}
+{% endif %}
+
+{% if default_models %}
+
+### Models
+
+The following models are available by default:
+
+{% for model in default_models %}
+- `{{ model.model_id }} {{ model.doc_string }}`
+{% endfor %}
+{% endif %}
+
+
+## Set up LM Studio
+
+Download LM Studio from [https://lmstudio.ai/download](https://lmstudio.ai/download). Start the server by opening LM Studio and navigating to the `Developer` Tab, or, run the CLI command `lms server start`.
+
+## Running Llama Stack with LM Studio
+
+You can do this via Conda (build code) or Docker which has a pre-built image.
+
+### Via Docker
+
+This method allows you to get started quickly without having to build the distribution code.
+
+```bash
+LLAMA_STACK_PORT=5001
+docker run \
+  -it \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ./run.yaml:/root/my-run.yaml \
+  llamastack/distribution-{{ name }} \
+  --yaml-config /root/my-run.yaml \
+  --port $LLAMA_STACK_PORT
+```
+
+### Via Conda
+
+```bash
+llama stack build --template lmstudio --image-type conda
+llama stack run ./run.yaml \
+  --port 5001
+```
--- a/llama_stack/templates/lmstudio/lmstudio.py
+++ b/llama_stack/templates/lmstudio/lmstudio.py
@ -0,0 +1,89 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from pathlib import Path
+
+from llama_stack.distribution.datatypes import Provider, ToolGroupInput
+from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
+from llama_stack.providers.remote.inference.lmstudio import LMStudioImplConfig
+from llama_stack.providers.remote.inference.lmstudio.models import MODEL_ENTRIES
+from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry
+
+
+def get_distribution_template() -> DistributionTemplate:
+    providers = {
+        "inference": ["remote::lmstudio"],
+        "safety": ["inline::llama-guard"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "agents": ["inline::meta-reference"],
+        "eval": ["inline::meta-reference"],
+        "datasetio": ["remote::huggingface", "inline::localfs"],
+        "scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
+        "telemetry": ["inline::meta-reference"],
+        "tool_runtime": [
+            "remote::tavily-search",
+            "inline::code-interpreter",
+            "inline::rag-runtime",
+        ],
+    }
+
+    name = "lmstudio"
+    lmstudio_provider = Provider(
+        provider_id="lmstudio",
+        provider_type="remote::lmstudio",
+        config=LMStudioImplConfig.sample_run_config(),
+    )
+
+    available_models = {
+        "lmstudio": MODEL_ENTRIES,
+    }
+    default_models = get_model_registry(available_models)
+    vector_io_provider = Provider(
+        provider_id="faiss",
+        provider_type="inline::faiss",
+        config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
+    )
+    default_tool_groups = [
+        ToolGroupInput(
+            toolgroup_id="builtin::websearch",
+            provider_id="tavily-search",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::rag",
+            provider_id="rag-runtime",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::code_interpreter",
+            provider_id="code-interpreter",
+        ),
+    ]
+
+    return DistributionTemplate(
+        name="lmstudio",
+        distro_type="self_hosted",
+        description="Use LM Studio for running LLM inference",
+        container_image=None,
+        template_path=Path(__file__).parent / "doc_template.md",
+        providers=providers,
+        available_models_by_provider=available_models,
+        run_configs={
+            "run.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [lmstudio_provider],
+                    "vector_io": [vector_io_provider],
+                },
+                default_models=default_models,
+                default_shields=[],
+                default_tool_groups=default_tool_groups,
+            ),
+        },
+        run_config_env_vars={
+            "LLAMA_STACK_PORT": (
+                "5001",
+                "Port for the Llama Stack distribution server",
+            ),
+        },
+    )
--- a/llama_stack/templates/lmstudio/report.md
+++ b/llama_stack/templates/lmstudio/report.md
@ -0,0 +1,44 @@
+# Report for cerebras distribution
+
+## Supported Models
+| Model Descriptor | cerebras |
+|:---|:---|
+| meta-llama/Llama-3-8B-Instruct | ✅ |
+| meta-llama/Llama-3-70B-Instruct | ✅ |
+| meta-llama/Llama-3.1-8B-Instruct | ✅ |
+| meta-llama/Llama-3.1-70B-Instruct | ✅ |
+| meta-llama/Llama-3.1-405B-Instruct-FP8 | ✅ |
+| meta-llama/Llama-3.2-1B-Instruct | ✅ |
+| meta-llama/Llama-3.2-3B-Instruct | ✅ |
+| meta-llama/Llama-3.2-11B-Vision-Instruct | ❌ |
+| meta-llama/Llama-3.2-90B-Vision-Instruct | ❌ |
+| meta-llama/Llama-3.3-70B-Instruct | ✅ |
+| meta-llama/Llama-Guard-3-11B-Vision | ❌  |
+| meta-llama/Llama-Guard-3-1B | ❌ |
+| meta-llama/Llama-Guard-3-8B | ❌ |
+| meta-llama/Llama-Guard-2-8B | ❌ |
+
+## Inference
+| Model | API | Capability | Test | Status |
+|:----- |:-----|:-----|:-----|:-----|
+| Llama-3.1-8B-Instruct | /chat_completion | streaming | test_text_chat_completion_streaming | ✅ |
+| Llama-3.2-11B-Vision-Instruct | /chat_completion | streaming | test_image_chat_completion_streaming | ❌ |
+| Llama-3.2-11B-Vision-Instruct | /chat_completion | non_streaming | test_image_chat_completion_non_streaming | ❌ |
+| Llama-3.1-8B-Instruct | /chat_completion | non_streaming | test_text_chat_completion_non_streaming | ✅ |
+| Llama-3.1-8B-Instruct | /chat_completion | tool_calling | test_text_chat_completion_with_tool_calling_and_streaming | ✅ |
+| Llama-3.1-8B-Instruct | /chat_completion | tool_calling | test_text_chat_completion_with_tool_calling_and_non_streaming | ✅ |
+| Llama-3.1-8B-Instruct | /completion | streaming | test_text_completion_streaming | ✅ |
+| Llama-3.1-8B-Instruct | /completion | non_streaming | test_text_completion_non_streaming | ✅ |
+| Llama-3.1-8B-Instruct | /completion | structured_output | test_text_completion_structured_output | ❌ |
+
+## Vector IO
+| API | Capability | Test | Status |
+|:-----|:-----|:-----|:-----|
+| /retrieve |  | test_vector_db_retrieve | ✅ |
+
+## Agents
+| API | Capability | Test | Status |
+|:-----|:-----|:-----|:-----|
+| /create_agent_turn | rag | test_rag_agent | ❓ |
+| /create_agent_turn | custom_tool | test_custom_tool | ❓ |
+| /create_agent_turn | code_execution | test_code_interpreter_for_attachments | ❓ |
--- a/llama_stack/templates/lmstudio/run.yaml
+++ b/llama_stack/templates/lmstudio/run.yaml
@ -0,0 +1,158 @@
+version: '2'
+image_name: lmstudio
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- safety
+- scoring
+- telemetry
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: lmstudio
+    provider_type: remote::lmstudio
+    config:
+      url: localhost:1234
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config:
+      excluded_categories: []
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/lmstudio}/faiss_store.db
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence_store:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/lmstudio}/agents_store.db
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/lmstudio}/meta_reference_eval.db
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/lmstudio}/huggingface_datasetio.db
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/lmstudio}/localfs_datasetio.db
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+    config: {}
+  - provider_id: llm-as-judge
+    provider_type: inline::llm-as-judge
+    config: {}
+  - provider_id: braintrust
+    provider_type: inline::braintrust
+    config:
+      openai_api_key: ${env.OPENAI_API_KEY:}
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/lmstudio/trace_store.db}
+  tool_runtime:
+  - provider_id: tavily-search
+    provider_type: remote::tavily-search
+    config:
+      api_key: ${env.TAVILY_SEARCH_API_KEY:}
+      max_results: 3
+  - provider_id: code-interpreter
+    provider_type: inline::code-interpreter
+    config: {}
+  - provider_id: rag-runtime
+    provider_type: inline::rag-runtime
+    config: {}
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/lmstudio}/registry.db
+models:
+- metadata: {}
+  model_id: meta-llama-3-8b-instruct
+  provider_id: lmstudio
+  provider_model_id: meta-llama-3-8b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama-3-70b-instruct
+  provider_id: lmstudio
+  provider_model_id: meta-llama-3-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama-3.1-8b-instruct
+  provider_id: lmstudio
+  provider_model_id: meta-llama-3.1-8b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama-3.1-70b-instruct
+  provider_id: lmstudio
+  provider_model_id: meta-llama-3.1-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: llama-3.2-1b-instruct
+  provider_id: lmstudio
+  provider_model_id: llama-3.2-1b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: llama-3.2-3b-instruct
+  provider_id: lmstudio
+  provider_model_id: llama-3.2-3b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: llama-3.2-70b-instruct
+  provider_id: lmstudio
+  provider_model_id: llama-3.2-70b-instruct
+  model_type: llm
+- metadata:
+    embedding_dimension: 768
+    context_length: 2048
+  model_id: nomic-embed-text-v1.5
+  provider_id: lmstudio
+  provider_model_id: nomic-embed-text-v1.5
+  model_type: embedding
+- metadata:
+    embedding_dimension: 384
+  model_id: all-minilm-l6-v2
+  provider_id: lmstudio
+  provider_model_id: all-minilm-l6-v2
+  model_type: embedding
+shields: []
+vector_dbs: []
+datasets: []
+scoring_fns: []
+benchmarks: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::rag
+  provider_id: rag-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter
+server:
+  port: 8321