v0.0.53

meta-llama/llama-stack

版本发布时间: 2024-11-21 06:18:00

meta-llama/llama-stack最新发布版本:v0.0.63(2024-12-18 15:17:43)

🚀 Initial Release Notes for Llama Stack!

Added

Resource-oriented design for models, shields, memory banks, datasets and eval tasks
Persistence for registered objects with distribution
Ability to persist memory banks created for FAISS
PostgreSQL KVStore implementation
Environment variable placeholder support in run.yaml files
Comprehensive Zero-to-Hero notebooks and quickstart guides
Support for quantized models in Ollama
Vision models support for Together, Fireworks, Meta-Reference, and Ollama, and vLLM
Bedrock distribution with safety shields support
Evals API with task registration and scoring functions
MMLU and SimpleQA benchmark scoring functions
Huggingface dataset provider integration for benchmarks
Support for custom dataset registration from local paths
Benchmark evaluation CLI tools with visualization tables
RAG evaluation scoring functions and metrics
Local persistence for datasets and eval tasks

Changed

Split safety into distinct providers (llama-guard, prompt-guard, code-scanner)
Changed provider naming convention (impls → inline, adapters → remote)
Updated API signatures for dataset and eval task registration
Restructured folder organization for providers
Enhanced Docker build configuration
Added version prefixing for REST API routes
Enhanced evaluation task registration workflow
Improved benchmark evaluation output formatting
Restructured evals folder organization for better modularity

Removed

llama stack configure command

What's Changed

Update download command by @Wauplin in https://github.com/meta-llama/llama-stack/pull/9
Update fbgemm version by @jianyuh in https://github.com/meta-llama/llama-stack/pull/12
Add CLI reference docs by @dltn in https://github.com/meta-llama/llama-stack/pull/14
Added Ollama as an inference impl by @hardikjshah in https://github.com/meta-llama/llama-stack/pull/20
Hide older models by @dltn in https://github.com/meta-llama/llama-stack/pull/23
Introduce Llama stack distributions by @ashwinb in https://github.com/meta-llama/llama-stack/pull/22
Rename inline -> local by @dltn in https://github.com/meta-llama/llama-stack/pull/24
Avoid using nearly double the memory needed by @ashwinb in https://github.com/meta-llama/llama-stack/pull/30
Updates to prompt for tool calls by @hardikjshah in https://github.com/meta-llama/llama-stack/pull/29
RFC-0001-The-Llama-Stack by @raghotham in https://github.com/meta-llama/llama-stack/pull/8
Add API keys to AgenticSystemConfig instead of relying on dotenv by @ashwinb in https://github.com/meta-llama/llama-stack/pull/33
update cli ref doc by @jeffxtang in https://github.com/meta-llama/llama-stack/pull/34
fixed bug in download not enough disk space condition by @sisminnmaw in https://github.com/meta-llama/llama-stack/pull/35
Updated cli instructions with additonal details for each subcommands by @varunfb in https://github.com/meta-llama/llama-stack/pull/36
Updated URLs and addressed feedback by @varunfb in https://github.com/meta-llama/llama-stack/pull/37
Fireworks basic integration by @benjibc in https://github.com/meta-llama/llama-stack/pull/39
Together AI basic integration by @Nutlope in https://github.com/meta-llama/llama-stack/pull/43
Update LICENSE by @raghotham in https://github.com/meta-llama/llama-stack/pull/47
Add patch for SSE event endpoint responses by @dltn in https://github.com/meta-llama/llama-stack/pull/50
API Updates: fleshing out RAG APIs, introduce "llama stack" CLI command by @ashwinb in https://github.com/meta-llama/llama-stack/pull/51
[inference] Add a TGI adapter by @ashwinb in https://github.com/meta-llama/llama-stack/pull/52
upgrade llama_models by @benjibc in https://github.com/meta-llama/llama-stack/pull/55
Query generators for RAG query by @hardikjshah in https://github.com/meta-llama/llama-stack/pull/54
Add Chroma and PGVector adapters by @ashwinb in https://github.com/meta-llama/llama-stack/pull/56
API spec update, client demo with Stainless SDK by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/58
Enable Bing search by @hardikjshah in https://github.com/meta-llama/llama-stack/pull/59
add safety to openapi spec by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/62
Add config file based CLI by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/60
Simplified Telemetry API and tying it to logger by @ashwinb in https://github.com/meta-llama/llama-stack/pull/57
[Inference] Use huggingface_hub inference client for TGI adapter by @hanouticelina in https://github.com/meta-llama/llama-stack/pull/53
Support data: in URL for memory. Add ootb support for pdfs by @hardikjshah in https://github.com/meta-llama/llama-stack/pull/67
Remove request wrapper migration by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/64
CLI Update: build -> configure -> run by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/69
API Updates by @ashwinb in https://github.com/meta-llama/llama-stack/pull/73
Unwrap ChatCompletionRequest for context_retriever by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/75
CLI - add back build wizard, configure with name instead of build.yaml by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/74
CLI: add build templates support, move imports by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/77
fix prompt with name args by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/80
Fix memory URL parsing by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/81
Allow TGI adaptor to have non-standard llama model names by @hardikjshah in https://github.com/meta-llama/llama-stack/pull/84
[API Updates] Model / shield / memory-bank routing + agent persistence + support for private headers by @ashwinb in https://github.com/meta-llama/llama-stack/pull/92
Bedrock Guardrails comiting after rebasing the fork by @rsgrewal-aws in https://github.com/meta-llama/llama-stack/pull/96
Bedrock Inference Integration by @poegej in https://github.com/meta-llama/llama-stack/pull/94
Support for Llama3.2 models and Swift SDK by @ashwinb in https://github.com/meta-llama/llama-stack/pull/98
fix safety using inference by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/99
Fixes typo for setup instruction for starting Llama Stack Server section by @abhishekmishragithub in https://github.com/meta-llama/llama-stack/pull/103
Make TGI adapter compatible with HF Inference API by @Wauplin in https://github.com/meta-llama/llama-stack/pull/97
Fix links & format by @machina-source in https://github.com/meta-llama/llama-stack/pull/104
docs: fix typo by @dijonkitchen in https://github.com/meta-llama/llama-stack/pull/107
LG safety fix by @kplawiak in https://github.com/meta-llama/llama-stack/pull/108
Minor typos, HuggingFace -> Hugging Face by @marklysze in https://github.com/meta-llama/llama-stack/pull/113
Reordered pip install and llama model download by @KarthiDreamr in https://github.com/meta-llama/llama-stack/pull/112
Update getting_started.ipynb by @delvingdeep in https://github.com/meta-llama/llama-stack/pull/117
fix: 404 link to agentic system repository by @moldhouse in https://github.com/meta-llama/llama-stack/pull/118
Fix broken links in RFC-0001-llama-stack.md by @bhimrazy in https://github.com/meta-llama/llama-stack/pull/134
Validate name in llama stack build by @russellb in https://github.com/meta-llama/llama-stack/pull/128
inference: Fix download command in error msg by @russellb in https://github.com/meta-llama/llama-stack/pull/133
configure: Fix a error msg typo by @russellb in https://github.com/meta-llama/llama-stack/pull/131
docs: Note how to use podman by @russellb in https://github.com/meta-llama/llama-stack/pull/130
add env for LLAMA_STACK_CONFIG_DIR by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/137
[bugfix] fix duplicate api endpoints by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/139
Use inference APIs for executing Llama Guard by @ashwinb in https://github.com/meta-llama/llama-stack/pull/121
fixing safety inference and safety adapter for new API spec. Pinned t… by @yogishbaliga in https://github.com/meta-llama/llama-stack/pull/105
[CLI] remove dependency on CONDA_PREFIX in CLI by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/144
[bugfix] fix #146 by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/147
Extract provider data properly (attempt 2) by @ashwinb in https://github.com/meta-llama/llama-stack/pull/148
is_multimodal accepts core_model_id not model itself. by @wizardbc in https://github.com/meta-llama/llama-stack/pull/153
fix broken bedrock inference provider by @moritalous in https://github.com/meta-llama/llama-stack/pull/151
Fix podman+selinux compatibility by @russellb in https://github.com/meta-llama/llama-stack/pull/132
docker: Install in editable mode for dev purposes by @russellb in https://github.com/meta-llama/llama-stack/pull/160
[CLI] simplify docker run by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/159
Add a RoutableProvider protocol, support for multiple routing keys by @ashwinb in https://github.com/meta-llama/llama-stack/pull/163
docker: Check for selinux before using --security-opt by @russellb in https://github.com/meta-llama/llama-stack/pull/167
Adds markdown-link-check and fixes a broken link by @codefromthecrypt in https://github.com/meta-llama/llama-stack/pull/165
[bugfix] conda path lookup by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/179
fix prompt guard by @ashwinb in https://github.com/meta-llama/llama-stack/pull/177
inference: Add model option to client by @russellb in https://github.com/meta-llama/llama-stack/pull/170
[CLI] avoid configure twice by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/171
Check that the model is found before use. by @AshleyT3 in https://github.com/meta-llama/llama-stack/pull/182
Add 'url' property to Redis KV config by @Minutis in https://github.com/meta-llama/llama-stack/pull/192
Inline vLLM inference provider by @russellb in https://github.com/meta-llama/llama-stack/pull/181
add databricks provider by @prithu-dasgupta in https://github.com/meta-llama/llama-stack/pull/83
add Weaviate memory adapter by @zainhas in https://github.com/meta-llama/llama-stack/pull/95
download: improve help text by @russellb in https://github.com/meta-llama/llama-stack/pull/204
Fix ValueError in case chunks are empty by @Minutis in https://github.com/meta-llama/llama-stack/pull/206
refactor docs by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/209
README.md: Add vLLM to providers table by @russellb in https://github.com/meta-llama/llama-stack/pull/207
Add .idea to .gitignore by @terrytangyuan in https://github.com/meta-llama/llama-stack/pull/216
[bugfix] Fix logprobs on meta-reference impl by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/213
Add classifiers in setup.py by @terrytangyuan in https://github.com/meta-llama/llama-stack/pull/217
Add function for stopping inference by @kebbbnnn in https://github.com/meta-llama/llama-stack/pull/224
JSON serialization for parallel processing queue by @dltn in https://github.com/meta-llama/llama-stack/pull/232
Remove "routing_table" and "routing_key" concepts for the user by @ashwinb in https://github.com/meta-llama/llama-stack/pull/201
ci: Run pre-commit checks in CI by @russellb in https://github.com/meta-llama/llama-stack/pull/176
Fix incorrect completion() signature for Databricks provider by @terrytangyuan in https://github.com/meta-llama/llama-stack/pull/236
Enable pre-commit on main branch by @terrytangyuan in https://github.com/meta-llama/llama-stack/pull/237
Switch to pre-commit/action by @terrytangyuan in https://github.com/meta-llama/llama-stack/pull/239
Remove request arg from chat completion response processing by @terrytangyuan in https://github.com/meta-llama/llama-stack/pull/240
Fix broken rendering in Google Colab by @frntn in https://github.com/meta-llama/llama-stack/pull/247
Docker compose scripts for remote adapters by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/241
Update getting_started.md by @MeDott29 in https://github.com/meta-llama/llama-stack/pull/260
Add llama download support for multiple models with comma-separated list by @tamdogood in https://github.com/meta-llama/llama-stack/pull/261
config templates restructure, docs by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/262
[bugfix] fix case for agent when memory bank registered without specifying provider_id by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/264
Add an option to not use elastic agents for meta-reference inference by @ashwinb in https://github.com/meta-llama/llama-stack/pull/269
Make all methods async def again; add completion() for meta-reference by @ashwinb in https://github.com/meta-llama/llama-stack/pull/270
Add vLLM inference provider for OpenAI compatible vLLM server by @terrytangyuan in https://github.com/meta-llama/llama-stack/pull/178
Update event_logger.py by @nehal-a2z in https://github.com/meta-llama/llama-stack/pull/275
llama stack distributions / templates / docker refactor by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/266
add more distro templates by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/279
first version of readthedocs by @raghotham in https://github.com/meta-llama/llama-stack/pull/278
add completion() for ollama by @dineshyv in https://github.com/meta-llama/llama-stack/pull/280
[Evals API] [1/n] Initial API by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/287
Add REST api example for chat_completion by @subramen in https://github.com/meta-llama/llama-stack/pull/286
feat: Qdrant Vector index support by @Anush008 in https://github.com/meta-llama/llama-stack/pull/221
Add support for Structured Output / Guided decoding by @ashwinb in https://github.com/meta-llama/llama-stack/pull/281
[bug] Fix import conflict for SamplingParams by @subramen in https://github.com/meta-llama/llama-stack/pull/285
Added implementations for get_agents_session, delete_agents_session and delete_agents by @cheesecake100201 in https://github.com/meta-llama/llama-stack/pull/267
[Evals API][2/n] datasets / datasetio meta-reference implementation by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/288
Added tests for persistence by @cheesecake100201 in https://github.com/meta-llama/llama-stack/pull/274
Support structured output for Together by @ashwinb in https://github.com/meta-llama/llama-stack/pull/289
dont set num_predict for all providers by @dineshyv in https://github.com/meta-llama/llama-stack/pull/294
Fix issue w/ routing_table api getting added when router api is not specified by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/298
New quantized models by @ashwinb in https://github.com/meta-llama/llama-stack/pull/301
[Evals API][3/n] scoring_functions / scoring meta-reference implementations by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/296
completion() for tgi by @dineshyv in https://github.com/meta-llama/llama-stack/pull/295
[enhancement] added templates and enhanced readme by @heyjustinai in https://github.com/meta-llama/llama-stack/pull/307
Fix for get_agents_session by @cheesecake100201 in https://github.com/meta-llama/llama-stack/pull/300
fix broken --list-templates with adding build.yaml files for packaging by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/327
Added hadamard transform for spinquant by @sacmehta in https://github.com/meta-llama/llama-stack/pull/326
[Evals API][4/n] evals with generation meta-reference impl by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/303
completion() for together by @dineshyv in https://github.com/meta-llama/llama-stack/pull/324
completion() for fireworks by @dineshyv in https://github.com/meta-llama/llama-stack/pull/329
[Evals API][6/n] meta-reference llm as judge, registration for ScoringFnDefs by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/330
update distributions compose/readme by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/338
distro readmes with model serving instructions by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/339
[Evals API][7/n] braintrust scoring provider by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/333
Kill --name from llama stack build by @ashwinb in https://github.com/meta-llama/llama-stack/pull/340
Do not cache pip by @stevegrubb in https://github.com/meta-llama/llama-stack/pull/349
add dynamic clients for all APIs by @ashwinb in https://github.com/meta-llama/llama-stack/pull/348
fix bedrock impl by @dineshyv in https://github.com/meta-llama/llama-stack/pull/359
[docs] update documentations by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/356
pgvector fixes by @dineshyv in https://github.com/meta-llama/llama-stack/pull/369
persist registered objects with distribution by @dineshyv in https://github.com/meta-llama/llama-stack/pull/354
Significantly simpler and malleable test setup by @ashwinb in https://github.com/meta-llama/llama-stack/pull/360
Correct a traceback in vllm by @stevegrubb in https://github.com/meta-llama/llama-stack/pull/366
add postgres kvstoreimpl by @dineshyv in https://github.com/meta-llama/llama-stack/pull/374
add ability to persist memory banks created for faiss by @dineshyv in https://github.com/meta-llama/llama-stack/pull/375
fix postgres config validation by @dineshyv in https://github.com/meta-llama/llama-stack/pull/380
Enable vision models for (Together, Fireworks, Meta-Reference, Ollama) by @ashwinb in https://github.com/meta-llama/llama-stack/pull/376
Kill llama stack configure by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/371
fix routing tables look up key for memory bank by @dineshyv in https://github.com/meta-llama/llama-stack/pull/383
add bedrock distribution code by @dineshyv in https://github.com/meta-llama/llama-stack/pull/358
Enable remote::vllm by @ashwinb in https://github.com/meta-llama/llama-stack/pull/384
Directory rename: providers/impls -> providers/inline, providers/adapters -> providers/remote by @ashwinb in https://github.com/meta-llama/llama-stack/pull/381
fix safety signature mismatch by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/388
Remove the safety adapter for Together; we can just use "meta-reference" by @ashwinb in https://github.com/meta-llama/llama-stack/pull/387
[LlamaStack][Fireworks] Update client and add unittest by @benjibc in https://github.com/meta-llama/llama-stack/pull/390
[bugfix] fix together data validator by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/393
Add provider deprecation support; change directory structure by @ashwinb in https://github.com/meta-llama/llama-stack/pull/397
Factor out create_dist_registry by @dltn in https://github.com/meta-llama/llama-stack/pull/398
[docs] refactor remote-hosted distro by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/402
[Evals API][10/n] API updates for EvalTaskDef + new test migration by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/379
Resource oriented design for shields by @dineshyv in https://github.com/meta-llama/llama-stack/pull/399
Add pip install helper for test and direct scenarios by @dltn in https://github.com/meta-llama/llama-stack/pull/404
migrate model to Resource and new registration signature by @dineshyv in https://github.com/meta-llama/llama-stack/pull/410
[Docs] Zero-to-Hero notebooks and quick start documentation by @heyjustinai in https://github.com/meta-llama/llama-stack/pull/368
Distributions updates (slight updates to ollama, add inline-vllm and remote-vllm) by @ashwinb in https://github.com/meta-llama/llama-stack/pull/408
added quickstart w ollama and toolcalling using together by @heyjustinai in https://github.com/meta-llama/llama-stack/pull/413
Split safety into (llama-guard, prompt-guard, code-scanner) by @ashwinb in https://github.com/meta-llama/llama-stack/pull/400
fix duplicate deploy in compose.yaml by @subramen in https://github.com/meta-llama/llama-stack/pull/417
[Evals API][11/n] huggingface dataset provider + mmlu scoring fn by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/392
Folder restructure for evals/datasets/scoring by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/419
migrate memory banks to Resource and new registration by @dineshyv in https://github.com/meta-llama/llama-stack/pull/411
migrate dataset to resource by @dineshyv in https://github.com/meta-llama/llama-stack/pull/420
migrate evals to resource by @dineshyv in https://github.com/meta-llama/llama-stack/pull/421
migrate scoring fns to resource by @dineshyv in https://github.com/meta-llama/llama-stack/pull/422
Rename all inline providers with an inline:: prefix by @ashwinb in https://github.com/meta-llama/llama-stack/pull/423
fix tests after registration migration & rename meta-reference -> basic / llm_as_judge provider by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/424
fix eval task registration by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/426
fix fireworks data validator by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/427
Allow specifying resources in StackRunConfig by @ashwinb in https://github.com/meta-llama/llama-stack/pull/425
Enable sane naming of registered objects with defaults by @ashwinb in https://github.com/meta-llama/llama-stack/pull/429
Remove the "ShieldType" concept by @ashwinb in https://github.com/meta-llama/llama-stack/pull/430
Inference to use provider resource id to register and validate by @dineshyv in https://github.com/meta-llama/llama-stack/pull/428
Kill "remote" providers and fix testing with a remote stack properly by @ashwinb in https://github.com/meta-llama/llama-stack/pull/435
add inline:: prefix for localfs provider by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/441
change schema -> dataset_schema for Dataset class by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/442
change schema -> dataset_schema for register_dataset api by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/443
PR-437-Fixed bug to allow system instructions after first turn by @cheesecake100201 in https://github.com/meta-llama/llama-stack/pull/440
add support for ${env.FOO_BAR} placeholders in run.yaml files by @ashwinb in https://github.com/meta-llama/llama-stack/pull/439
model registration in ollama and vllm check against the available models in the provider by @dineshyv in https://github.com/meta-llama/llama-stack/pull/446
Added link to the Colab notebook of the Llama Stack lesson on the Llama 3.2 course on DLAI by @jeffxtang in https://github.com/meta-llama/llama-stack/pull/445
make distribution registry thread safe and other fixes by @dineshyv in https://github.com/meta-llama/llama-stack/pull/449
local persistent for hf dataset provider by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/451
Support model resource updates and deletes by @dineshyv in https://github.com/meta-llama/llama-stack/pull/452
init registry once by @dineshyv in https://github.com/meta-llama/llama-stack/pull/450
local persistence for eval tasks by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/453
Fix build configure deprecation message by @hickeyma in https://github.com/meta-llama/llama-stack/pull/456
Support parallel downloads for llama model download by @ashwinb in https://github.com/meta-llama/llama-stack/pull/448
Add a verify-download command to llama CLI by @ashwinb in https://github.com/meta-llama/llama-stack/pull/457
unregister for memory banks and remove update API by @dineshyv in https://github.com/meta-llama/llama-stack/pull/458
move hf addapter->remote by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/459
await initialize in faiss by @dineshyv in https://github.com/meta-llama/llama-stack/pull/463
fix faiss serialize and serialize of index by @dineshyv in https://github.com/meta-llama/llama-stack/pull/464
Extend shorthand support for the llama stack run command by @vladimirivic in https://github.com/meta-llama/llama-stack/pull/465
[Agentic Eval] add ability to run agents generation by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/469
Auto-generate distro yamls + docs by @ashwinb in https://github.com/meta-llama/llama-stack/pull/468
Allow models to be registered as long as llama model is provided by @dineshyv in https://github.com/meta-llama/llama-stack/pull/472
get stack run config based on template name by @dineshyv in https://github.com/meta-llama/llama-stack/pull/477
add quantized model ollama support by @wukaixingxp in https://github.com/meta-llama/llama-stack/pull/471
Update kotlin client docs by @Riandy in https://github.com/meta-llama/llama-stack/pull/476
remove pydantic namespace warnings using model_config by @mattf in https://github.com/meta-llama/llama-stack/pull/470
fix llama stack build for together & llama stack build from templates by @yanxi0830 in https://github.com/meta-llama/llama-stack/pull/479
Add version to REST API url by @ashwinb in https://github.com/meta-llama/llama-stack/pull/478
support adding alias for models without hf repo/sku entry by @dineshyv in https://github.com/meta-llama/llama-stack/pull/481
update quick start to have the working instruction by @chuenlok in https://github.com/meta-llama/llama-stack/pull/467
add changelog by @dineshyv in https://github.com/meta-llama/llama-stack/pull/487
Added optional md5 validate command once download is completed by @varunfb in https://github.com/meta-llama/llama-stack/pull/486
Support Tavily as built-in search tool. by @iseeyuan in https://github.com/meta-llama/llama-stack/pull/485
Reorganizing Zero to Hero Folder structure by @heyjustinai in https://github.com/meta-llama/llama-stack/pull/447
fall to back to read from chroma/pgvector when not in cache by @dineshyv in https://github.com/meta-llama/llama-stack/pull/489
register with provider even if present in stack by @dineshyv in https://github.com/meta-llama/llama-stack/pull/491
Make run yaml optional so dockers can start with just --env by @ashwinb in https://github.com/meta-llama/llama-stack/pull/492

New Contributors

@Wauplin made their first contribution in https://github.com/meta-llama/llama-stack/pull/9
@jianyuh made their first contribution in https://github.com/meta-llama/llama-stack/pull/12
@dltn made their first contribution in https://github.com/meta-llama/llama-stack/pull/14
@hardikjshah made their first contribution in https://github.com/meta-llama/llama-stack/pull/20
@raghotham made their first contribution in https://github.com/meta-llama/llama-stack/pull/8
@jeffxtang made their first contribution in https://github.com/meta-llama/llama-stack/pull/34
@sisminnmaw made their first contribution in https://github.com/meta-llama/llama-stack/pull/35
@varunfb made their first contribution in https://github.com/meta-llama/llama-stack/pull/36
@benjibc made their first contribution in https://github.com/meta-llama/llama-stack/pull/39
@Nutlope made their first contribution in https://github.com/meta-llama/llama-stack/pull/43
@hanouticelina made their first contribution in https://github.com/meta-llama/llama-stack/pull/53
@rsgrewal-aws made their first contribution in https://github.com/meta-llama/llama-stack/pull/96
@poegej made their first contribution in https://github.com/meta-llama/llama-stack/pull/94
@abhishekmishragithub made their first contribution in https://github.com/meta-llama/llama-stack/pull/103
@machina-source made their first contribution in https://github.com/meta-llama/llama-stack/pull/104
@dijonkitchen made their first contribution in https://github.com/meta-llama/llama-stack/pull/107
@marklysze made their first contribution in https://github.com/meta-llama/llama-stack/pull/113
@KarthiDreamr made their first contribution in https://github.com/meta-llama/llama-stack/pull/112
@delvingdeep made their first contribution in https://github.com/meta-llama/llama-stack/pull/117
@moldhouse made their first contribution in https://github.com/meta-llama/llama-stack/pull/118
@bhimrazy made their first contribution in https://github.com/meta-llama/llama-stack/pull/134
@russellb made their first contribution in https://github.com/meta-llama/llama-stack/pull/128
@yogishbaliga made their first contribution in https://github.com/meta-llama/llama-stack/pull/105
@wizardbc made their first contribution in https://github.com/meta-llama/llama-stack/pull/153
@moritalous made their first contribution in https://github.com/meta-llama/llama-stack/pull/151
@codefromthecrypt made their first contribution in https://github.com/meta-llama/llama-stack/pull/165
@AshleyT3 made their first contribution in https://github.com/meta-llama/llama-stack/pull/182
@Minutis made their first contribution in https://github.com/meta-llama/llama-stack/pull/192
@prithu-dasgupta made their first contribution in https://github.com/meta-llama/llama-stack/pull/83
@zainhas made their first contribution in https://github.com/meta-llama/llama-stack/pull/95
@terrytangyuan made their first contribution in https://github.com/meta-llama/llama-stack/pull/216
@kebbbnnn made their first contribution in https://github.com/meta-llama/llama-stack/pull/224
@frntn made their first contribution in https://github.com/meta-llama/llama-stack/pull/247
@MeDott29 made their first contribution in https://github.com/meta-llama/llama-stack/pull/260
@tamdogood made their first contribution in https://github.com/meta-llama/llama-stack/pull/261
@nehal-a2z made their first contribution in https://github.com/meta-llama/llama-stack/pull/275
@dineshyv made their first contribution in https://github.com/meta-llama/llama-stack/pull/280
@subramen made their first contribution in https://github.com/meta-llama/llama-stack/pull/286
@Anush008 made their first contribution in https://github.com/meta-llama/llama-stack/pull/221
@cheesecake100201 made their first contribution in https://github.com/meta-llama/llama-stack/pull/267
@heyjustinai made their first contribution in https://github.com/meta-llama/llama-stack/pull/307
@sacmehta made their first contribution in https://github.com/meta-llama/llama-stack/pull/326
@stevegrubb made their first contribution in https://github.com/meta-llama/llama-stack/pull/349
@hickeyma made their first contribution in https://github.com/meta-llama/llama-stack/pull/456
@vladimirivic made their first contribution in https://github.com/meta-llama/llama-stack/pull/465
@wukaixingxp made their first contribution in https://github.com/meta-llama/llama-stack/pull/471
@Riandy made their first contribution in https://github.com/meta-llama/llama-stack/pull/476
@mattf made their first contribution in https://github.com/meta-llama/llama-stack/pull/470
@chuenlok made their first contribution in https://github.com/meta-llama/llama-stack/pull/467
@iseeyuan made their first contribution in https://github.com/meta-llama/llama-stack/pull/485

Full Changelog: https://github.com/meta-llama/llama-stack/commits/v0.0.53

相关地址：原始地址下载(tar) 下载(zip)

查看：2024-11-21发行的版本