llama-stack
llama-stack copied to clipboard
meta-llama
Composable building blocks to build Llama Apps
This allows a set of rules to be defined for determining access to resources. The rules are (loosely) based on the cedar policy format. A rule defines a list of...
# What does this PR do? PR to implement WatsonX health check ## Test Plan PR includes the unit test to test the added health check implementation feature.
# What does this PR do? To add health status check for remote VLLM ## Test Plan PR includes the unit test to test the added health check implementation feature.
# What does this PR do? the HF SFTTrainer supports distributed training using FSDP. Add a new recipe, `finetune_multi_device` which supports multi-GPU (cuda) training using FSDP and optionally LoRA. transformers...
### 🚀 Describe the new functionality needed Users should be able to upload a file in the Playground UI that is then sent to the llama stack server and is...
### 🚀 Describe the new functionality needed We want to enable developers to see the full trace of a Llama Stack agent, which includes actions that may be executed by...
### 🚀 Describe the new functionality needed Implement the ability to Chat with the Llama Stack using basic inference ### 💡 Why is this needed? What if we don't build...
# What does this PR do? Adds input validation for mode in RagQueryConfig This will prevent users from inputting search modes other than `vector` and `keyword` for the time being...
# What does this PR do? This PR creates a webmethod for deleting open AI responses, adds and implementation for it and makes an integration test for the OpenAI delete...
### 🚀 Describe the new functionality needed Let's support the following two variables for the OTLP endpoint when generating configuration, instead of generating a constant. ``` OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf ``` The...
Metadata
Owner
Metadata
Composable building blocks to build Llama Apps