1 Release published by 1 person

• v0.1.7

  published Mar 14, 2025

82 Pull requests merged by 22 people

• feat(dataset api): (1.6/n) fix all iterrows callsites

  #1660 merged Mar 16, 2025

• feat(dataset api): (1.5/n) fix dataset registeration

  #1659 merged Mar 15, 2025

• feat(dataset api): (1.4/n) fix resolver signature mismatch

  #1658 merged Mar 15, 2025

• feat(dataset api): (1.3/n) patch OpenAPI gen for datasetio->datasets

  #1657 merged Mar 15, 2025

• feat(dataset api): (1.2/n) datasets.iterrorws pagination api updates

  #1656 merged Mar 15, 2025

• Web updates to point to latest releases for Mobile SDK

  #1650 merged Mar 15, 2025

• docs: add additional guidance around using virtualenv

  #1642 merged Mar 14, 2025

• feat: [new open benchmark] BFCL_v3

  #1578 merged Mar 14, 2025

• feat: add support for logging config in the run.yaml

  #1408 merged Mar 14, 2025

• chore: Add pre-commit check to sync api spec docs

  #1609 merged Mar 14, 2025

• chore: Add ./scripts/unit-tests.sh

  #1515 merged Mar 14, 2025

• fix: OpenAPI with provider get

  #1627 merged Mar 14, 2025

• fix: change dog.jpg path in test_vision_inference.py

  #1624 merged Mar 14, 2025

• fix: Fix pre-commit check

  #1628 merged Mar 14, 2025

• fix: Clarify llama model prompt-format help text

  #1010 merged Mar 14, 2025

• feat(dataset api): (1.1/n) dataset api implementation fix pre-commit

  #1625 merged Mar 13, 2025

• refactor: move all datetime.now() calls to UTC

  #1589 merged Mar 13, 2025

• docs: Add OpenAI, Anthropic, Gemini to inference API providers table

  #1622 merged Mar 13, 2025

• feat: add provider API for listing and inspecting provider info

  #1429 merged Mar 13, 2025

• build(deps): bump astral-sh/setup-uv from 4 to 5

  #1620 merged Mar 13, 2025

• chore: Always check that git merge conflict markers are not present

  #1610 merged Mar 13, 2025

• test: turn off recordable mock for now

  #1616 merged Mar 13, 2025

• docs: Add OpenAI, Anthropic, Gemini to API providers table

  #1617 merged Mar 13, 2025

• ci: add GitHub Action to close stale issues and PRs

  #1613 merged Mar 13, 2025

• ci(ollama): add GitHub Actions workflow for integration tests

  #1546 merged Mar 13, 2025

• test: re record responses after client sync

  #1615 merged Mar 13, 2025

• fix: clean up test imports

  #1600 merged Mar 13, 2025

• ci: add dynamic CI job to test templates

  #1230 merged Mar 13, 2025

• fix: passthrough provider template + fix

  #1612 merged Mar 13, 2025

• test: add unit test to ensure all config types are instantiable

  #1601 merged Mar 13, 2025

• fix: openapi spec gen

  #1602 merged Mar 13, 2025

• build: remove .python-version

  #1513 merged Mar 13, 2025

• feat(api): remove tool_name from ToolResponseMessage

  #1599 merged Mar 13, 2025

• test: code exec on mac

  #1549 merged Mar 13, 2025

• ci: add html report to unit test artifacts

  #1576 merged Mar 13, 2025

• chore: simplify _get_tool_defs

  #1384 merged Mar 13, 2025

• chore: refactor Agent toolgroup processing

  #1381 merged Mar 13, 2025

• feat: Add new compact MetricInResponse type

  #1593 merged Mar 12, 2025

• docs: add unit test badge to README

  #1591 merged Mar 12, 2025

• fix: logging

  #1598 merged Mar 12, 2025

• fix: fix build error in context.py

  #1595 merged Mar 12, 2025

• chore: deprecate ToolResponseMessage in agent.resume API

  #1566 merged Mar 12, 2025

• feat: Add back inference metrics and preserve context variables across asyncio boundary

  #1552 merged Mar 12, 2025

• fix: fix precommit

  #1594 merged Mar 12, 2025

• fix: fix passthrough inference provider to make it work for agent

  #1577 merged Mar 12, 2025

• feat: Add open benchmark template codegen

  #1579 merged Mar 12, 2025

• fix: respect log_level in uvicorn and third party libs

  #1524 merged Mar 12, 2025

• ci: run unit tests on all supported python versions

  #1575 merged Mar 12, 2025

• chore: Expand mypy exclusions list

  #1543 merged Mar 12, 2025

• feat: convert typehints from client_tool to litellm format

  #1565 merged Mar 12, 2025

• test: adding an e2e test for measuring TTFT

  #1568 merged Mar 11, 2025

• fix: Fixed bad file name in inline::localfs

  #1358 merged Mar 11, 2025

• fix: fix llama stack run with missing agent impl

  #1559 merged Mar 11, 2025

• fix: remove Llama-3.2-1B-Instruct for fireworks

  #1558 merged Mar 11, 2025

• test: loosen Python 3.10 version for unit tests

  #1547 merged Mar 11, 2025

• feat: add support for LLAMA_STACK_LOG_FILE

  #1450 merged Mar 11, 2025

• feat(api): list agents / sessions and get agent

  #1410 merged Mar 11, 2025

• fix: Multiple fixes for server shutdown (fix lifespan handling; fix handling CancelledError when raised by provider; let uvicorn handle signals)

  #1495 merged Mar 11, 2025

• docs: Small nits in llama CLI reference

  #1542 merged Mar 11, 2025

• chore: fix typing hints for get_provider_impl deps arguments

  #1544 merged Mar 11, 2025

• docs: Remove duplicate docs on api docs generator

  #1534 merged Mar 11, 2025

• fix: Add missing shutdown handler for TorchtunePostTrainingImpl

  #1535 merged Mar 11, 2025

• revert: feat(server): Use system packages for execution

  #1551 merged Mar 11, 2025

• fix: tracing fixes for trace context propogation across coroutines

  #1522 merged Mar 11, 2025

• feat: [new open benchmark] Math 500

  #1538 merged Mar 11, 2025

• fix: Use --with-editable to capture accurate code coverage reporting

  #1532 merged Mar 10, 2025

• fix: revert to using faiss for ollama distro

  #1530 merged Mar 10, 2025

• feat(server): Use system packages for execution

  #1252 merged Mar 10, 2025

• docs: improve integration test doc

  #1502 merged Mar 10, 2025

• build: revamp "test" dependencies from pyproject

  #1468 merged Mar 10, 2025

• test: add inspect unit test

  #1417 merged Mar 10, 2025

• chore: add color to Env Variable message

  #1525 merged Mar 10, 2025

• fix: Disable async loop warning messages during test run

  #1526 merged Mar 10, 2025

• fix: server logging

  #1521 merged Mar 10, 2025

• chore: Together async client

  #1510 merged Mar 10, 2025

• fix: include jinja2 as a core llama-stack dependency

  #1529 merged Mar 10, 2025

• refactor: ImageType to LlamaStackImageType

  #1500 merged Mar 10, 2025

• chore: Display code coverage for unit tests in PR builds

  #1512 merged Mar 10, 2025

• docs: update ollama doc url

  #1508 merged Mar 10, 2025

• fix: update getting_started structured decoding cell

  #1523 merged Mar 10, 2025

• docs: improve eval doc

  #1501 merged Mar 10, 2025

• docs: update prompt for websearch example

  #1520 merged Mar 10, 2025

43 Pull requests opened by 23 people

• feat: Switch synthetic data generation API to jobs pattern

  #1533 opened Mar 10, 2025

• feat: Add unit tests for `LlamaCLIParser` to increase code coverage

  #1536 opened Mar 11, 2025

• feat: Convert `config` positional arg to `--config` in `llama stack run`

  #1541 opened Mar 11, 2025

• chore: fix mypy violations in post_training modules

  #1548 opened Mar 11, 2025

• fix: agents with non-llama model

  #1550 opened Mar 11, 2025

• feat: Implement system packages option for --image-type

  #1555 opened Mar 11, 2025

• feat(agent): support multiple tool groups

  #1556 opened Mar 11, 2025

• feat: Document preprocessing API endpoints and their integration in the RAG ingestion process

  #1563 opened Mar 11, 2025

• [WIP] Add support for RamaLama

  #1564 opened Mar 11, 2025

• feat(api): (1/n) datasets api clean up

  #1573 opened Mar 11, 2025

• feat: [new benchmark] math 500 with llm as judge

  #1581 opened Mar 12, 2025

• fix: Add the option to not verify SSL at remote-vllm provider

  #1585 opened Mar 12, 2025

• feat(providers): sambanova updated to use LiteLLM openai-compat

  #1596 opened Mar 12, 2025

• feat: add /jobs API

  #1597 opened Mar 12, 2025

• feat: Adding support for MongoDB Atlas vector store and vector search

  #1603 opened Mar 13, 2025

• docs: [RFC] RAG Reranking Feature for Llama-Stack

  #1605 opened Mar 13, 2025

• feat: implementation for agent/session list and describe

  #1606 opened Mar 13, 2025

• fix: solve unregister_toolgroup error

  #1608 opened Mar 13, 2025

• ci: Add dependabot scans for Python deps

  #1618 opened Mar 13, 2025

• fix: to issue 1586

  #1619 opened Mar 13, 2025

• feat: Proposal for Triage Role [resolves #1561]

  #1621 opened Mar 13, 2025

• feat(auth, rfc): Add support for Bearer (api_key) Authentication

  #1626 opened Mar 13, 2025

• chore: Add links and badges to both unit and integration tests

  #1632 opened Mar 14, 2025

• [draft] huggingface-ilab full-precision model fine-tuning

  #1634 opened Mar 14, 2025

• fix: return 4xx for non-existent resources in GET requests

  #1635 opened Mar 14, 2025

• ci(ollama): run more integration tests

  #1636 opened Mar 14, 2025

• fix: fixed import error

  #1637 opened Mar 14, 2025

• feat(api): remove List* response types and nils for get/list

  #1639 opened Mar 14, 2025

• feat(api): don't return a payload on file delete

  #1640 opened Mar 14, 2025

• refactor: simplify command execution and remove PTY handling

  #1641 opened Mar 14, 2025

• chore: enable ruff for ./scripts too

  #1643 opened Mar 14, 2025

• ci: limit PR testing based on modified files

  #1644 opened Mar 14, 2025

• chore: convert blocking calls to async calls in some providers

  #1645 opened Mar 14, 2025

• chore: consolidate scripts under ./scripts directory

  #1646 opened Mar 14, 2025

• feat: [new open benchmark] DocVQA

  #1647 opened Mar 14, 2025

• feat: LM Studio inference integration

  #1649 opened Mar 14, 2025

• fix: Fix pre-commit check

  #1651 opened Mar 15, 2025

• chore: Remove unused cursor rules

  #1653 opened Mar 15, 2025

• chore: Make code interpreter async

  #1654 opened Mar 15, 2025

• docs: Simplify vLLM deployment in K8s deployment guide

  #1655 opened Mar 15, 2025

• feat(api): (2/n) evaluation + grader api

  #1664 opened Mar 17, 2025

• fix: passthrough impl response.content.text

  #1665 opened Mar 17, 2025

• fix: Fixed import errors for UI and playground

  #1666 opened Mar 17, 2025

15 Issues closed by 8 people

• Pytest failed on test_vision_inference.py with meta-reference gpu : cannot identify image file <_io.BytesIO object..

  #1553 closed Mar 16, 2025

• Quick start guide with ollama-distribution fails; No module named 'jinja2'

  #1638 closed Mar 14, 2025

• remote vLLM provider fails agents tests

  #1144 closed Mar 14, 2025

• Add enterprise vector database

  #120 closed Mar 14, 2025

• Create shared openai-compatible inference adapter

  #193 closed Mar 14, 2025

• Quick Start Ollama Docker ModuleNotFoundError: No module named 'jinja2'

  #1607 closed Mar 13, 2025

• provider shutdown methods are not currently executed

  #188 closed Mar 13, 2025

• api: make ToolResponseMessage.tool_name optional

  #1421 closed Mar 13, 2025

• api: deprecate ToolResponseMessage in agent.resume_turn

  #1431 closed Mar 12, 2025

• bug: type casting issue & streaming support for passthrough provider

  #1560 closed Mar 12, 2025

• Help Needed for understanding

  #155 closed Mar 12, 2025

• inline::localfs datasetio provider writes to file named "uri=<the file name>"

  #1357 closed Mar 11, 2025

• Context retrieval only works for first user message

  #444 closed Mar 11, 2025

• Add ability to list and describe agents

  #1294 closed Mar 11, 2025

• Failed to do tool-call in ReAct agent example with 90B meta-reference-gpu server

  #1519 closed Mar 10, 2025

22 Issues opened by 16 people

• test_text_inference pytest failed on vllm-gpu 0.1.7 server

  #1662 opened Mar 16, 2025

• Failed to run distribution-remote-vllm with AMD ROCm vllm container as the provider

  #1661 opened Mar 16, 2025

• Require all builds passing before merging

  #1652 opened Mar 15, 2025

• Add a remote-vllm integration test to GitHub Actions workflow.

  #1648 opened Mar 14, 2025

• Quick Start steps result in sqlite3 error

  #1633 opened Mar 14, 2025

• Improve RAG as attachment behaviour in agent

  #1631 opened Mar 14, 2025

• correct GET endpoints to not return None

  #1630 opened Mar 14, 2025

• Enable merge queue

  #1629 opened Mar 14, 2025

• Deprecate `/v1/inspect/providers`

  #1623 opened Mar 13, 2025

• Custom distribution image with remote VLLM provider fails to start

  #1604 opened Mar 13, 2025

• Streamline Job management for long running tasks (eval, synthetic data generation, post_training etc.)

  #1587 opened Mar 12, 2025

• Error when adding model-context-protocol toolgroup via yaml-config

  #1586 opened Mar 12, 2025

• MCP procotol handling issues

  #1584 opened Mar 12, 2025

• feat: Add apis and support for Model Context Protocol resources and prompts

  #1567 opened Mar 11, 2025

• Simplify imports

  #1554 opened Mar 11, 2025

• Support for custom TLS certificates: vllm-remote

  #1545 opened Mar 11, 2025

• Stack start fails with ModuleNotFoundError: No module named 'openai'

  #1540 opened Mar 11, 2025

• Agent doesn't always select custom tool, even with `tool_choice="required"`

  #1539 opened Mar 11, 2025

• Unregistering a toolgroup fails with "500 Internal Server Error"

  #1537 opened Mar 11, 2025

• json_response_format=True did not return valid json with meta-reference 90B vision server

  #1531 opened Mar 10, 2025

• CI: Semantic title check triggers on incorrect PR

  #1518 opened Mar 10, 2025

• broken latest Image

  #1511 opened Mar 10, 2025

115 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• feat: Implement async job execution for torchtune training

  #1437 commented on Mar 14, 2025 • 20 new comments

• feat: add health to all providers through providers endpoint

  #1418 commented on Mar 14, 2025 • 10 new comments

• feat: Add nemo customizer

  #1448 commented on Mar 14, 2025 • 9 new comments

• feat: Add warning message for unsupported param

  #1422 commented on Mar 11, 2025 • 4 new comments

• ci: Add scheduled workflow to update changelog

  #1503 commented on Mar 14, 2025 • 3 new comments

• feat: Created Playground Containerfile and Image Workflow

  #1256 commented on Mar 17, 2025 • 3 new comments

• feat: Qdrant inline provider

  #1273 commented on Mar 17, 2025 • 2 new comments

• Mem0 Integration: Add mem0 as memory provider for RAG

  #914 commented on Mar 14, 2025 • 1 new comment

• " errors" when processing output stream

  #66 commented on Mar 14, 2025 • 0 new comments

• Allow Ollama to run other models besides the llama family

  #123 commented on Mar 14, 2025 • 0 new comments

• LLM hallucinating while tool calling

  #124 commented on Mar 14, 2025 • 0 new comments

• llama stack build on Windows

  #140 commented on Mar 14, 2025 • 0 new comments

• llama cli does not work on mac Sequoia

  #143 commented on Mar 14, 2025 • 0 new comments

• VLLM / OpenAI Compatible endpoint support

  #152 commented on Mar 14, 2025 • 0 new comments

• `llama-stack run` with meta reference inference provider fails with ModuleNotFoundError

  #180 commented on Mar 14, 2025 • 0 new comments

• stack tool cannot support large models with a .pth extension downloaded from Meta

  #190 commented on Mar 14, 2025 • 0 new comments

• Are there any available tools that can convert the original .pth to safetensors

  #191 commented on Mar 14, 2025 • 0 new comments

• I am puzzled as to why stack needs to link it to the address [: ffff: 0.0.2.208]

  #194 commented on Mar 14, 2025 • 0 new comments

• vllm: test and fix tool support

  #199 commented on Mar 14, 2025 • 0 new comments

• vllm: improve container support

  #200 commented on Mar 14, 2025 • 0 new comments

• vllm: expand configuration support

  #208 commented on Mar 14, 2025 • 0 new comments

• Add top_k output tokens w/ corresponding logprobs

  #214 commented on Mar 14, 2025 • 0 new comments

• Tool Registry for Agents

  #234 commented on Mar 14, 2025 • 0 new comments

• 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

  #242 commented on Mar 14, 2025 • 0 new comments

• how to build llamastack/distribution-meta-reference-gpu from Dockerfile?

  #919 commented on Mar 11, 2025 • 0 new comments

• AttributeError: 'ChatCompletionResponse' object has no attribute 'event'

  #246 commented on Mar 14, 2025 • 0 new comments

• [W socket.cpp:697] [c10d] The IPv6 network addresses of (1.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.ip6.arpa, 50714) cannot be retrieved (gai error: 8 - nodename nor servname provided, or not known).

  #248 commented on Mar 14, 2025 • 0 new comments

• missing target image architecture

  #253 commented on Mar 14, 2025 • 0 new comments

• pytorch CUDA not found in host that has CUDA with working pytorch

  #257 commented on Mar 14, 2025 • 0 new comments

• Create a remote memory provider for pinecone

  #268 commented on Mar 14, 2025 • 0 new comments

• I keep getting 405 forbidden

  #273 commented on Mar 14, 2025 • 0 new comments

• Create a memory provider for mongoDB

  #302 commented on Mar 14, 2025 • 0 new comments

• Object of type SearchEngineType is not JSON serializable

  #282 commented on Mar 14, 2025 • 0 new comments

• feat(sqlite-vec): enable keyword search for sqlite-vec

  #1439 commented on Mar 11, 2025 • 0 new comments

• docs: add notes to websearch tool and two extra example scripts

  #1354 commented on Mar 11, 2025 • 0 new comments

• feat: support nvidia hosted vision models (llama 3.2 11b/90b)

  #1278 commented on Mar 10, 2025 • 0 new comments

• fix: add ollama embedding config and fix sqlite_vec db

  #1255 commented on Mar 10, 2025 • 0 new comments

• feat: added nvidia as safety provider

  #1248 commented on Mar 16, 2025 • 0 new comments

• docs: move sections from README to docs

  #1143 commented on Mar 10, 2025 • 0 new comments

• docs: remove redundant installation instructions

  #1138 commented on Mar 10, 2025 • 0 new comments

• feat: add FiddleCube guard as a safety provider

  #1037 commented on Mar 10, 2025 • 0 new comments

• refactor: support downloading any model from HF

  #1001 commented on Mar 11, 2025 • 0 new comments

• feat: CentML AI Inference Provider Integration

  #810 commented on Mar 13, 2025 • 0 new comments

• Portkey AI Inference Provider Integration

  #672 commented on Mar 10, 2025 • 0 new comments

• feat: azure ai inference support

  #364 commented on Mar 14, 2025 • 0 new comments

• Free up GPU memory after unregistering model in meta reference inference

  #768 commented on Mar 17, 2025 • 0 new comments

• Why can't I use my llama stack? Can anyone help me?

  #373 commented on Mar 16, 2025 • 0 new comments

• Better error message for fireworks invalid response_format

  #650 commented on Mar 15, 2025 • 0 new comments

• [RFC] Support multi modal retrieval on top of llama stack, inference provider side

  #667 commented on Mar 15, 2025 • 0 new comments

• Portkey AI inference Provier support

  #671 commented on Mar 15, 2025 • 0 new comments

• Feature Request: Option to Delete a Memory

  #682 commented on Mar 15, 2025 • 0 new comments

• Inference Pytest Failed at text_chat_completion_with_tool_calling scenarios

  #1185 commented on Mar 14, 2025 • 0 new comments

• Support for providers outside of this codebase

  #658 commented on Mar 14, 2025 • 0 new comments

• Colons in filenames when using llama download make them incompatible with windows.

  #42 commented on Mar 14, 2025 • 0 new comments

• Checkpoint Cannot Be Found For Llama 405B Model

  #44 commented on Mar 14, 2025 • 0 new comments

• Inference Failed Because of '500 Internal Server Error'

  #45 commented on Mar 14, 2025 • 0 new comments

• FP8 Quantization Does Not Work

  #46 commented on Mar 14, 2025 • 0 new comments

• Unable to deploy Llama-Guard-3-1B using llama-stack build

  #119 commented on Mar 14, 2025 • 0 new comments

• Ollama Distro : Duplicate BOS Tokens in Prompt

  #913 commented on Mar 11, 2025 • 0 new comments

• llama stack build not working with prefix based environments

  #804 commented on Mar 11, 2025 • 0 new comments

• meta-llama/Llama-3.2-3B-Instruct-QLORA_INT4_EO8 not found

  #824 commented on Mar 11, 2025 • 0 new comments

• Determining model reference when deploying Ollama model with docker.

  #784 commented on Mar 11, 2025 • 0 new comments

• Upload arm64 docker images where relevant

  #406 commented on Mar 11, 2025 • 0 new comments

• httpx.UnsupportedProtocol: Request URL is missing an 'http://' or 'https://' protocol.

  #466 commented on Mar 11, 2025 • 0 new comments

• Issue saving and querying PDF to vector store (meta-reference)

  #342 commented on Mar 11, 2025 • 0 new comments

• Create the distribution of AMD ROCm GPU

  #341 commented on Mar 11, 2025 • 0 new comments

• What configs input when build from distributions/meta-reference-gpu/build.yaml

  #321 commented on Mar 11, 2025 • 0 new comments

• wrong UNIX filesystem root

  #255 commented on Mar 11, 2025 • 0 new comments

• docker images are too large

  #254 commented on Mar 11, 2025 • 0 new comments

• Deleting a stack

  #225 commented on Mar 11, 2025 • 0 new comments

• How to run llama3.2 90B self hosted using llama-stack?

  #215 commented on Mar 11, 2025 • 0 new comments

• `llama stack run my-local-stack` causes pydantic error

  #174 commented on Mar 11, 2025 • 0 new comments

• fbgemm-gpu isn't officially supported on mac - optional dependency?

  #164 commented on Mar 11, 2025 • 0 new comments

• Build fails on MacOS with docker

  #162 commented on Mar 11, 2025 • 0 new comments

• Prompt-format in cli-reference does not show image

  #158 commented on Mar 11, 2025 • 0 new comments

• Docker Build Fails Due to Invalid File Path in ADD Command

  #141 commented on Mar 11, 2025 • 0 new comments

• git clone of repo fails, pip install lama-stack does not provide llama cli tool

  #127 commented on Mar 11, 2025 • 0 new comments

• llama stack build with docker not working: config yaml not found

  #114 commented on Mar 11, 2025 • 0 new comments

• How do you use the docker distribution?

  #106 commented on Mar 11, 2025 • 0 new comments

• Introduce Hybrid Search API using SQLite FTS5 + Vector search

  #1158 commented on Mar 11, 2025 • 0 new comments

• [RFC] Integrate Hyperparameter Optimization into Llama Stack

  #1319 commented on Mar 11, 2025 • 0 new comments

• Enable inline multi-device model tuning via `post_training` API

  #1427 commented on Mar 10, 2025 • 0 new comments

• feat: showcase retrieval improvements in rag lifecycle notebook

  #1478 commented on Mar 10, 2025 • 0 new comments

• Endpoint testing for hosted endpoints

  #1367 commented on Mar 10, 2025 • 0 new comments

• Agent workflow dependency graph

  #1438 commented on Mar 10, 2025 • 0 new comments

• EleutherAI/lm-evaluation-harness /eval provider

  #1069 commented on Mar 10, 2025 • 0 new comments

• Support AMD ROCm GPU distribution

  #320 commented on Mar 14, 2025 • 0 new comments

• Server webmethod endpoint and llama-stack-spec.yaml file mismatch

  #322 commented on Mar 14, 2025 • 0 new comments

• Guardrail Loading Failed with Unexpected Large GPU Memory Requirement at Multi-GPU Server

  #328 commented on Mar 14, 2025 • 0 new comments

• How to specify the model type using the pre-build docker?

  #331 commented on Mar 14, 2025 • 0 new comments

• Ollama inference issue - llama3.2 not registered

  #332 commented on Mar 14, 2025 • 0 new comments

• [enhancement] Add support for llama 3.2 models using Amazon AWS bedrock inference

  #334 commented on Mar 14, 2025 • 0 new comments

• TypeError: expected str, bytes or os.PathLike object, not NoneType

  #336 commented on Mar 14, 2025 • 0 new comments

• ValueError: `Llama3.1-8B-Instruct` not registered. Make sure there is an Inference provider serving this model.

  #345 commented on Mar 14, 2025 • 0 new comments

• Model ids that contains a colon throws error when trying to install on Windows

  #347 commented on Mar 14, 2025 • 0 new comments

• Run ollama gpu distribution failed

  #350 commented on Mar 14, 2025 • 0 new comments

• Path misinterpretation in llama model command: C: misread as C-

  #513 commented on Mar 14, 2025 • 0 new comments

• Improve errors in client when there are server errors

  #434 commented on Mar 14, 2025 • 0 new comments

• 500 when uploading large documents to memory bank

  #582 commented on Mar 14, 2025 • 0 new comments

• Permission denied error on running 'llama-stack-client providers list'

  #691 commented on Mar 14, 2025 • 0 new comments

• Executing setup.py build on Windows 11 throws a UnicodeDecodeError.

  #724 commented on Mar 14, 2025 • 0 new comments

• Move `ReactAgent` to the server

  #1370 commented on Mar 13, 2025 • 0 new comments

• Registering datasets with name of existing dataset

  #1449 commented on Mar 12, 2025 • 0 new comments

• Improve CRUD on scoring function llm-as-judge

  #1454 commented on Mar 12, 2025 • 0 new comments

• api: simplify inference API by deprecating sampling_params

  #1368 commented on Mar 12, 2025 • 0 new comments

• Implement a 1 line utility to get started with a llama stack distro on local

  #1374 commented on Mar 12, 2025 • 0 new comments

• Llama Stack Playground

  #1373 commented on Mar 12, 2025 • 0 new comments

• together and fireworks adaptors docs

  #1297 commented on Mar 12, 2025 • 0 new comments

• Batch Inference Support

  #1071 commented on Mar 12, 2025 • 0 new comments

• Question regarding agents and sessions APIs

  #197 commented on Mar 11, 2025 • 0 new comments

• Nondeterministic Agent Tests

  #1182 commented on Mar 11, 2025 • 0 new comments

• Add Support for Kubernetes

  #186 commented on Mar 11, 2025 • 0 new comments

• Support post-training / pre-deployment security testing models and systems

  #1054 commented on Mar 11, 2025 • 0 new comments

• Sometimes getting `Error exporting span to SQLite: Cannot operate on a closed database.` when running RAG agent example from getting started document

  #999 commented on Mar 11, 2025 • 0 new comments

• how to llamastack/distribution-inline-vllm from Dockerfile?

  #920 commented on Mar 11, 2025 • 0 new comments