llama-stack

llama-stack copied to clipboard

### System Info Collecting environment information... PyTorch version: 2.1.2+cu118 Is debug build: False CUDA used to build PyTorch: 11.8 ROCM used to build PyTorch: N/A OS: Ubuntu 22.04.4 LTS (x86_64)...

quic-haijunz

getting_started.ipynb link on llama.com is a 404

1

### System Info iPhone Mobile Safari ### 🐛 Describe the bug This "Learn more" link on https://www.llama.com/ links to https://github.com/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb which is a 404.  ### Expected behavior It should...

simonw

Improve errors in client when there are server errors

2

### System Info Python=3.11 CUDA ### Information - [ ] The official example scripts - [ ] My own modified scripts ### 🐛 Describe the bug Need to propagate server...

raghotham

# What does this PR do? Contributes to issue #432 - Adds tool calls to Groq provider - Enables tool call integration tests ### PR Train - https://github.com/meta-llama/llama-stack/pull/609 - https://github.com/meta-llama/llama-stack/pull/630...

aidando73

[#432] Add Groq Provider - chat completions

1

# What does this PR do? Contributes towards issue (#432) - Groq text chat completions - Streaming - All the sampling params that Groq supports A lot of inspiration taken...

aidando73

- Implemented a Python function to extract tags from the model identifier field for dynamic population. - Enabled users to specify tags manually when registering a model. - Tags are...

HabebNawatha

# What does this PR do? Pinning zero2hero to 0.0.61 and updated readme ## Test Plan Please describe: - Did a end to end test on the server and inference...

heyjustinai

Add automatic PyPI release GitHub workflow

1

This PR adds a workflow to automatically publish the package (including attestations) to Python upon tag/release creation. Note that this relies on trusted publishing: https://docs.pypi.org/trusted-publishers/

terrytangyuan

Add Remote Inference Adapter for Groq

2

### 🚀 The feature, motivation and pitch It would be very helpful to have out-of-the-box Inference Provider for [GroqCloud](https://groq.com/groqcloud/). Thanks! ### Alternatives _No response_ ### Additional context _No response_

sanjayk-github-dev

Explanation of Sampling Param semantics in documentation

1

### 🚀 Describe the new functionality needed [Sampling params](https://github.com/meta-llama/llama-models/blob/main/models/datatypes.py#L24) semantics - strategy: greedy | top_k | top_p - temperature: Optional[float] = 0.0 - top_p: Optional[float] = 0.95 - top_k: Optional[int]...

mattf