meta-llama llama-stack issues

meta-llama / llama-stack

Composable building blocks to build Llama Apps

MIT License

4.63k stars 586 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

docs: include ollama link in quickstart

#504 sarthakgupta072 closed 3 hours ago
1
Add Ollama inference mocks

#503 vladimirivic opened 16 hours ago
0
ollama distro: can't find shield

#502 heyjustinai opened 18 hours ago
0
Updating Zero-to-hero-guide

#501 init27 closed 16 hours ago
0
Fix fp8 quantization script.

#500 liyunlu0618 closed 23 hours ago
1
use logging instead of prints

#499 dineshyv closed 20 hours ago
0
Fix fp8 quantization script.

#498 liyunlu0618 closed 1 day ago
0
Since we are pushing for HF repos, we should accept them in inference configs

#497 ashwinb closed 1 day ago
0
Don't depend on templates.py when print llama stack build messages

#496 ashwinb closed 1 day ago
0
O'zbekistonda turib amerikanskiy logist dispechirlar qancha daromad topish mumkin

#495 Kadamboy opened 1 day ago
1
Restructure docs

#494 dineshyv closed 1 day ago
2
append the error in the internal server error

#493 chuenlok opened 1 day ago
1
Make run yaml optional so dockers can start with just --env

#492 ashwinb closed 1 day ago
0
register with provider even if present in stack

#491 dineshyv closed 1 day ago
1
Adding memory provider mocks

#490 vladimirivic closed 9 hours ago
1
fall to back to read from chroma/pgvector when not in cache

#489 dineshyv closed 1 day ago
0
rebase

#488 init27 closed 2 days ago
0
add changelog

#487 dineshyv closed 2 days ago
0
Added optional md5 validate command once download is completed

#486 varunfb closed 2 days ago
0
Support Tavily as built-in search tool.

#485 iseeyuan closed 2 days ago
4
map llama model -> provider model id in ModelRegistryHelper

#484 mattf opened 2 days ago
0
Update Ollama supported llama model list

#483 hickeyma opened 3 days ago
1
[wip] Add cache for PGVector memory adapter

#482 hickeyma opened 3 days ago
0
support adding alias for models without hf repo/sku entry

#481 dineshyv closed 3 days ago
0
fix core model ids for ollama

#480 dineshyv closed 2 days ago
1
fix llama stack build for together & llama stack build from templates

#479 yanxi0830 closed 3 days ago
0
Add version to REST API url

#478 ashwinb closed 3 days ago
0
get stack run config based on template name

#477 dineshyv closed 3 days ago
1
Update kotlin client docs

#476 Riandy closed 3 days ago
0
Colab links in Zero-Hero would work?

#475 HamidShojanazeri closed 18 hours ago
2
Adding memory provider test fakes

#474 vladimirivic opened 3 days ago
2
Fix incorrect ollama port in ollama run.yaml template

#473 vladimirivic closed 3 days ago
1
Allow models to be registered as long as llama model is provided

#472 dineshyv closed 3 days ago
0
add quantized model ollama support

#471 wukaixingxp closed 3 days ago
1
remove pydantic namespace warnings using model_config

#470 mattf closed 3 days ago
0
[Agentic Eval] add ability to run agents generation

#469 yanxi0830 closed 3 days ago
0
Auto-generate distro yamls + docs

#468 ashwinb closed 3 days ago
0
update quick start to have the working instruction

#467 chuenlok closed 2 days ago
1
httpx.UnsupportedProtocol: Request URL is missing an 'http://' or 'https://' protocol.

#466 Drizzle2001 opened 6 days ago
0
Extend shorthand support for the `llama stack run` command

#465 vladimirivic closed 6 days ago
0
fix faiss serialize and serialize of index

#464 dineshyv closed 6 days ago
0
await initialize in faiss

#463 dineshyv closed 6 days ago
0
Enable more supported models with ollama

#462 yanxi0830 opened 6 days ago
1
Fix conda env names in distribution example run files

#461 hickeyma closed 3 days ago
1
[Adding new Inference provider] get error at runtime when the stack code is looking for a model to serve

#460 sanjayk-github-dev opened 1 week ago
12
move hf addapter->remote

#459 yanxi0830 closed 1 week ago
0
unregister for memory banks and remove update API

#458 dineshyv closed 1 week ago
6
Add a verify-download command to llama CLI

#457 ashwinb closed 1 week ago
0
Fix build configure deprecation message

#456 hickeyma closed 1 week ago
0
Add ability for local persistence for memory adapters

#455 yanxi0830 opened 1 week ago
5