llama-stack

llama-stack copied to clipboard

failed to run inference on 3.2 11B vision model

2

Hi, I'm trying to run inference on 11B vision model but faced this error running the client. I was able to download, build, config and run the server without issue....

roywei

llama stack run failed with AssertionError: Could not find checkpoint dir

1

using pyenv + venv + Docker, llama stack run failed and seems cannot found model directory ``` $ llama stack run my-local-stack + '[' -n '' ']' + '[' -z...

kun432

LLM hallucinating while tool calling

1

 The tool call shows something called as brary search which neither I have passed nor exists. I have only passed inbuilt tools which are brave_Search, wolfram alpha and code...

cheesecake100201

Failing to build llama-stack on Mac OS X

3

Followed Getting Started guide, tried to build locally on Mac OS 15.0 (M1): ```Collecting fairscale Using cached fairscale-0.4.13.tar.gz (266 kB) Installing build dependencies ... done Getting requirements to build wheel...

genbit

for agents API, provider data from the header is not parsed as for ag…

1

…ents there is no provider_data_validator meta-reference implementation. Added Together data validator as the provider_data_validator for now. Did some code changes accordingly. Tested it by running local instance of the llama-stack...

yogishbaliga

Add sambanova provider

1

### Why this PR We want to setup SambaNova as a remote inference provider for llama-stack. ### What is in the PR Integration with distribution OpenAI as a client ###...

snova-edwardm

Fix podman+selinux compatibility

7

commit c39ba235087291b3901cf2ddd68f5526e97ab67f Author: Russell Bryant Date: Fri Sep 27 14:05:18 2024 +0000 Fix podman+selinux compatibility When I ran `llama stack configure` for my `docker` based stack on my system using...

russellb

Ad vLLM provider support

1

The docs call out vLLM as an example of a possible provider implementation. I'm looking at writing that, so I wanted to open this issue to track the work. Feel...

russellb

Docker Build Fails Due to Invalid File Path in ADD Command

4

error message: `ERROR: failed to solve: failed to compute cache key: failed to calculate checksum of ref 15120e76-2864-4c89-91bc-9a3e64744d1d::jmn4a98bdl0q4ptn73a1s2iym: "/.local/share/virtualenvs/Llama_stack_chat-htDpca_X/lib/python3.10/site-packages/llama_stack/configs/distributions/docker/challama-build.yaml": not found ` Macos -- 14.6.1 M2

CarrotKan

llama stack build on Windows

4

Hello I'm trying to `llama stack build` on my Windows 10 machine. Facing following issue: > ModuleNotFoundError: No module named 'termios' Full error trace: ``` Traceback (most recent call last):...

that-rahul-guy