llama-stack

llama-stack copied to clipboard

This would help us catch pre-commit issues like the ones fixed in https://github.com/meta-llama/llama-stack/pull/236.

terrytangyuan

# DevX Flow ##### Step 1. Register Eval Dataset ``` python -m llama_stack.apis.datasets.client ``` ##### Step 2. Run Eval Scorer ``` python -m llama_stack.apis.evals.client ``` - (benchmark) run full preprocess->generation->postprocess->score...

yanxi0830

We need to have a capability to add new tools or disable/remove tools sometimes after an agent has been deployed. Similar to current methods with `@webmethod` decorators for agents, could...

onkarbhardwaj

Llama3.1-8B-Instruct,already there, but llama stack can not find it。conda and docker both doesn't work~~~~~

2

Failed to run stack through conda：llama stack run stack-3.2-1B --port 5000 --disable-ipv6 https://github.com/meta-llama/llama-stack/issues/194 ，I don't know why stack needs to link it to the address [: ffff: 0.0.2.208] Failed to...

Itime-ren

# Script Usage ``` $ cd scripts/docker/tgi $ ls compose.yaml tgi-run.yaml $ docker compose up ``` **Expected output** - TGI container is spawn up in port 5009 - Llama Stack...

yanxi0830

This is not used since we are processing the response, not the request.

terrytangyuan

I used the official Docker image and downloaded the weight file from Meta. The md5sum test proved that the file was fine, but it still failed to run, which left me confused

2

I used the official Docker image and downloaded the weight file from Meta. The md5sum test proved that the file was fine, but it still failed to run, which left...

Itime-ren

Does Quantization (FP8) support the Llama3.2-90B-Vision-Instruct model?

1

Hello, I encountered some problems when loading the Llama3.2-90B-Vision-Instruct model with FP8. Can you help me take a look? Version of llama_stack and llama_models: ``` llama_models == 0.0.41 llama_stack ==...

boanz

Address issue #233 , allowing users to pass a comma-separated list of model IDs with the --model-ids argument and matching meta URLs via --meta-url.

ABucket

Llama3.2-1B only reply "<|end_of_text|>"

3

Hi Expert, I just tried to to install llama-stack and run the test with **Llama3.2-1B** but I found the response is really weird. Since my GPU RAM is only 6GB,...

tw40210