phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-15 14:08:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs: update CHANGELOG.md for v0.2.17

Browse source 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
This commit is contained in:
ashwinb 2025-08-05 01:51:25 +00:00 • committed by github-actions[bot]
parent e565b91182
commit 3d048343c9
1 changed files with 358 additions and 339 deletions
Download patch file Download diff file Expand all files Collapse all files

53
CHANGELOG.md
View file

@ -1,5 +1,40 @@
# Changelog
# v0.2.17
Published on: 2025-08-05T01:51:14Z
## Highlights
* feat(tests): introduce inference record/replay to increase test reliability by @ashwinb in https://github.com/meta-llama/llama-stack/pull/2941
* fix(library_client): improve initialization error handling and prevent AttributeError by @mattf in https://github.com/meta-llama/llama-stack/pull/2944
* fix: use OLLAMA_URL to activate Ollama provider in starter by @ashwinb in https://github.com/meta-llama/llama-stack/pull/2963
* feat(UI): adding MVP playground UI by @franciscojavierarceo in https://github.com/meta-llama/llama-stack/pull/2828
* Standardization of errors (@nathan-weinberg)
* feat: Enable DPO training with HuggingFace inline provider by @Nehanth in https://github.com/meta-llama/llama-stack/pull/2825
* chore: rename templates to distributions by @ashwinb in https://github.com/meta-llama/llama-stack/pull/3035
---
# v0.2.16
Published on: 2025-07-28T23:35:23Z
## Highlights
* Automatic model registration for self-hosted providers (ollama and vllm currently). No need for `INFERENCE_MODEL` environment variables which need to be updated, etc.
* Much simplified starter distribution. Most `ENABLE_` env variables are now gone. When you set `VLLM_URL`, the `vllm` provider is auto-enabled. Similar for `MILVUS_URL`, `PGVECTOR_DB`, etc. Check the [run.yaml](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/templates/starter/run.yaml) for more details.
* All tests migrated to pytest now (thanks @Elbehery)
* DPO implementation in the post-training provider (thanks @Nehanth)
* (Huge!) Support for external APIs and providers thereof (thanks @leseb, @cdoern and others). This is a really big deal -- you can now add more APIs completely out of tree and experiment with them before (optionally) wanting to contribute back.
* `inline::vllm` provider is gone thank you very much
* several improvements to OpenAI inference implementations and LiteLLM backend (thanks @mattf)
* Chroma now supports Vector Store API (thanks @franciscojavierarceo).
* Authorization improvements: Vector Store/File APIs now supports access control (thanks @franciscojavierarceo); Telemetry read APIs are gated according to logged-in user's roles.
---
# v0.2.15
Published on: 2025-07-16T03:30:01Z
@ -451,7 +486,7 @@ GenAI application developers need more than just an LLM - they need to integrate
Llama Stack was created to provide developers with a comprehensive and coherent interface that simplifies AI application development and codifies best practices across the Llama ecosystem. Since our launch in September 2024, we have seen a huge uptick in interest in Llama Stack APIs by both AI developers and from partners building AI services with Llama models. Partners like Nvidia, Fireworks, and Ollama have collaborated with us to develop implementations across various APIs, including inference, memory, and safety.
With Llama Stack, you can easily build a RAG agent which can also search the web, do complex math, and custom tool calling. You can use telemetry to inspect those traces, and convert telemetry into evals datasets. And with Llama Stack’s plugin architecture and prepackage distributions, you choose to run your agent anywhere - in the cloud with our partners, deploy your own environment using virtualenv or Docker, operate locally with Ollama, or even run on mobile devices with our SDKs. Llama Stack offers unprecedented flexibility while also simplifying the developer experience.
With Llama Stack, you can easily build a RAG agent which can also search the web, do complex math, and custom tool calling. You can use telemetry to inspect those traces, and convert telemetry into evals datasets. And with Llama Stack’s plugin architecture and prepackage distributions, you choose to run your agent anywhere - in the cloud with our partners, deploy your own environment using virtualenv, conda, or Docker, operate locally with Ollama, or even run on mobile devices with our SDKs. Llama Stack offers unprecedented flexibility while also simplifying the developer experience.
## Release
After iterating on the APIs for the last 3 months, today we’re launching a stable release (V1) of the Llama Stack APIs and the corresponding llama-stack server and client packages(v0.1.0). We now have automated tests for providers. These tests make sure that all provider implementations are verified. Developers can now easily and reliably select distributions or providers based on their specific requirements.
@ -498,19 +533,3 @@ There are example standalone apps in llama-stack-apps.
---
# v0.1.0rc12
Published on: 2025-01-22T22:24:01Z
---
# v0.0.63
Published on: 2024-12-18T07:17:43Z
A small but important bug-fix release to update the URL datatype for the client-SDKs. The issue affected multimodal agentic turns especially.
**Full Changelog**: https://github.com/meta-llama/llama-stack/compare/v0.0.62...v0.0.63
---