forked from phoenix-oss/llama-stack-mirror

Composable building blocks to build Llama Apps

Find a file

yyymeta b79e0435de fix: avoid tensor memory error (#1688 ) # What does this PR do? we randomly get errors like the following, it's most likely due to accessing an object that is already deallocated ``` E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] Traceback (most recent call last): E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 90, in _wrap E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] fn(i, args) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 611, in _wrap E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] ret = record(fn)(args_) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] return f(args, kwargs) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/internal-llama-stack/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py", line 249, in worker_process_entrypoint E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] task = req_gen.send(result) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/internal-llama-stack/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py", line 156, in retrieve_requests E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] torch.distributed.broadcast_object_list( E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/distributed/c10d_logger.py", line 81, in wrapper E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] return func(args, **kwargs) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/distributed/distributed_c10d.py", line 3504, in broadcast_object_list E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] object_list[i] = _tensor_to_object(obj_view, obj_size, group) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/distributed/distributed_c10d.py", line 2961, in _tensor_to_object E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] return _unpickler(io.BytesIO(buf)).load() E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] EOFError: Ran out of input E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] Process SpawnProcess-1: Traceback (most recent call last): ``` ## Test Plan start server ``` llama-stack-client eval run-benchmark mmmu_v1 --model-id meta-llama/Llama-4-17B-Omni-Instruct --output-dir /tmp/mmmu_standard --num-examples 30 ``` [//]: # (## Documentation)		2025-03-18 16:17:29 -07:00
.github	ci: Add scheduled workflow to update changelog (#1503 )	2025-03-18 14:39:22 -07:00
distributions	feat: added nvidia as safety provider (#1248 )	2025-03-17 14:39:23 -07:00
docs	chore: fix mypy violations in post_training modules (#1548 )	2025-03-18 14:58:16 -07:00
llama_stack	fix: avoid tensor memory error (#1688 )	2025-03-18 16:17:29 -07:00
rfcs	chore: remove straggler references to llama-models (#1345 )	2025-03-01 14:26:03 -08:00
scripts	chore: enable ruff for ./scripts too (#1643 )	2025-03-18 12:17:21 -07:00
tests	feat: Qdrant inline provider (#1273 )	2025-03-18 14:04:21 -07:00
.gitignore	build: remove .python-version (#1513 )	2025-03-12 20:08:24 -07:00
.pre-commit-config.yaml	chore: consolidate scripts under ./scripts directory (#1646 )	2025-03-17 17:56:30 -04:00
.readthedocs.yaml	first version of readthedocs (#278 )	2024-10-22 10:15:58 +05:30
CHANGELOG.md	docs: Add v0.1.6 release notes to changelog (#1506 )	2025-03-08 16:20:08 -08:00
CODE_OF_CONDUCT.md	Initial commit	2024-07-23 08:32:33 -07:00
CONTRIBUTING.md	docs: fix broken test path in CONTRIBUTING.md (#1679 )	2025-03-18 13:39:46 -07:00
LICENSE	Update LICENSE (#47 )	2024-08-29 07:39:50 -07:00
MANIFEST.in	build: include .md (#1482 )	2025-03-07 12:10:52 -08:00
pyproject.toml	chore: fix mypy violations in post_training modules (#1548 )	2025-03-18 14:58:16 -07:00
README.md	docs: remove redundant installation instructions (#1138 )	2025-03-18 14:52:21 -07:00
requirements.txt	ci: Bump version to 0.1.7	2025-03-14 15:21:26 -07:00
SECURITY.md	Create SECURITY.md	2024-10-08 13:30:40 -04:00
uv.lock	feat: Qdrant inline provider (#1273 )	2025-03-18 14:04:21 -07:00

README.md

Llama Stack

Quick Start | Documentation | Colab Notebook

Llama Stack standardizes the core building blocks that simplify AI application development. It codifies best practices across the Llama ecosystem. More specifically, it provides

Unified API layer for Inference, RAG, Agents, Tools, Safety, Evals, and Telemetry.
Plugin architecture to support the rich ecosystem of different API implementations in various environments, including local development, on-premises, cloud, and mobile.
Prepackaged verified distributions which offer a one-stop solution for developers to get started quickly and reliably in any environment.
Multiple developer interfaces like CLI and SDKs for Python, Typescript, iOS, and Android.
Standalone applications as examples for how to build production-grade AI applications with Llama Stack.

Llama Stack Benefits

Flexible Options: Developers can choose their preferred infrastructure without changing APIs and enjoy flexible deployment choices.
Consistent Experience: With its unified APIs, Llama Stack makes it easier to build, test, and deploy AI applications with consistent application behavior.
Robust Ecosystem: Llama Stack is already integrated with distribution partners (cloud providers, hardware vendors, and AI-focused companies) that offer tailored infrastructure, software, and services for deploying Llama models.

By reducing friction and complexity, Llama Stack empowers developers to focus on what they do best: building transformative generative AI applications.

API Providers

Here is a list of the various API providers and available distributions that can help developers get started easily with Llama Stack.

API Provider Builder	Environments	Agents	Inference	Memory	Safety	Telemetry
Meta Reference	Single Node	✅	✅	✅	✅	✅
SambaNova	Hosted		✅
Cerebras	Hosted		✅
Fireworks	Hosted	✅	✅	✅
AWS Bedrock	Hosted		✅		✅
Together	Hosted	✅	✅		✅
Groq	Hosted		✅
Ollama	Single Node		✅
TGI	Hosted and Single Node		✅
NVIDIA NIM	Hosted and Single Node		✅
Chroma	Single Node			✅
PG Vector	Single Node			✅
PyTorch ExecuTorch	On-device iOS	✅	✅
vLLM	Hosted and Single Node		✅
OpenAI	Hosted		✅
Anthropic	Hosted		✅
Gemini	Hosted		✅

Distributions

A Llama Stack Distribution (or "distro") is a pre-configured bundle of provider implementations for each API component. Distributions make it easy to get started with a specific deployment scenario - you can begin with a local development setup (eg. ollama) and seamlessly transition to production (eg. Fireworks) without changing your application code. Here are some of the distributions we support:

Distribution	Llama Stack Docker	Start This Distribution
Meta Reference	llamastack/distribution-meta-reference-gpu	Guide
Meta Reference Quantized	llamastack/distribution-meta-reference-quantized-gpu	Guide
SambaNova	llamastack/distribution-sambanova	Guide
Cerebras	llamastack/distribution-cerebras	Guide
Ollama	llamastack/distribution-ollama	Guide
TGI	llamastack/distribution-tgi	Guide
Together	llamastack/distribution-together	Guide
Fireworks	llamastack/distribution-fireworks	Guide
vLLM	llamastack/distribution-remote-vllm	Guide

Documentation

Please checkout our Documentation page for more details.

CLI references
- llama (server-side) CLI Reference: Guide for using the llama CLI to work with Llama models (download, study prompts), and building/starting a Llama Stack distribution.
- llama (client-side) CLI Reference: Guide for using the llama-stack-client CLI, which allows you to query information about the distribution.
Getting Started
- Quick guide to start a Llama Stack server.
- Jupyter notebook to walk-through how to use simple text and vision inference llama_stack_client APIs
- The complete Llama Stack lesson Colab notebook of the new Llama 3.2 course on Deeplearning.ai.
- A Zero-to-Hero Guide that guide you through all the key components of llama stack with code samples.
Contributing
- Adding a new API Provider to walk-through how to add a new API provider.

Llama Stack Client SDKs

Language	Client SDK	Package
Python	llama-stack-client-python
Swift	llama-stack-client-swift
Typescript	llama-stack-client-typescript
Kotlin	llama-stack-client-kotlin

Check out our client SDKs for connecting to a Llama Stack server in your preferred language, you can choose from python, typescript, swift, and kotlin programming languages to quickly build your applications.

You can find more example scripts with client SDKs to talk with the Llama Stack server in our llama-stack-apps repo.