mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-20 19:56:59 +00:00
llama stack distributions / templates / docker refactor (#266)
* docker compose ollama * comment * update compose file * readme for distributions * readme * move distribution folders * move distribution/templates to distributions/ * rename * kill distribution/templates * readme * readme * build/developer cookbook/new api provider * developer cookbook * readme * readme * [bugfix] fix case for agent when memory bank registered without specifying provider_id (#264) * fix case where memory bank is registered without provider_id * memory test * agents unit test * Add an option to not use elastic agents for meta-reference inference (#269) * Allow overridding checkpoint_dir via config * Small rename * Make all methods `async def` again; add completion() for meta-reference (#270) PR #201 had made several changes while trying to fix issues with getting the stream=False branches of inference and agents API working. As part of this, it made a change which was slightly gratuitous. Namely, making chat_completion() and brethren "def" instead of "async def". The rationale was that this allowed the user (within llama-stack) of this to use it as: ``` async for chunk in api.chat_completion(params) ``` However, it causes unnecessary confusion for several folks. Given that clients (e.g., llama-stack-apps) anyway use the SDK methods (which are completely isolated) this choice was not ideal. Let's revert back so the call now looks like: ``` async for chunk in await api.chat_completion(params) ``` Bonus: Added a completion() implementation for the meta-reference provider. Technically should have been another PR :) * Improve an important error message * update ollama for llama-guard3 * Add vLLM inference provider for OpenAI compatible vLLM server (#178) This PR adds vLLM inference provider for OpenAI compatible vLLM server. * Create .readthedocs.yaml Trying out readthedocs * Update event_logger.py (#275) spelling error * vllm * build templates * delete templates * tmp add back build to avoid merge conflicts * vllm * vllm --------- Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com> Co-authored-by: Yuan Tang <terrytangyuan@gmail.com> Co-authored-by: raghotham <rsm@meta.com> Co-authored-by: nehal-a2z <nehal@coderabbit.ai>
This commit is contained in:
Xi Yan
GitHub
parent
c995219731
commit
23210e8679
32 changed files with 850 additions and 335 deletions
|
|
@ -1,10 +0,0 @@
|
|||
name: local-bedrock-conda-example
|
||||
distribution_spec:
|
||||
description: Use Amazon Bedrock APIs.
|
||||
providers:
|
||||
inference: remote::bedrock
|
||||
memory: meta-reference
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: conda
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
name: local-cpu
|
||||
distribution_spec:
|
||||
description: remote inference + local safety/agents/memory
|
||||
docker_image: null
|
||||
providers:
|
||||
inference:
|
||||
- remote::ollama
|
||||
- remote::tgi
|
||||
- remote::together
|
||||
- remote::fireworks
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
memory: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: docker
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
name: local-databricks
|
||||
distribution_spec:
|
||||
description: Use Databricks for running LLM inference
|
||||
providers:
|
||||
inference: remote::databricks
|
||||
memory: meta-reference
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: conda
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
name: local-fireworks
|
||||
distribution_spec:
|
||||
description: Use Fireworks.ai for running LLM inference
|
||||
providers:
|
||||
inference: remote::fireworks
|
||||
memory: meta-reference
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: conda
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
name: local-gpu
|
||||
distribution_spec:
|
||||
description: Use code from `llama_stack` itself to serve all llama stack APIs
|
||||
providers:
|
||||
inference: meta-reference
|
||||
memory: meta-reference
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: docker
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
name: local-hf-endpoint
|
||||
distribution_spec:
|
||||
description: "Like local, but use Hugging Face Inference Endpoints for running LLM inference.\nSee https://hf.co/docs/api-endpoints."
|
||||
providers:
|
||||
inference: remote::hf::endpoint
|
||||
memory: meta-reference
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: conda
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
name: local-hf-serverless
|
||||
distribution_spec:
|
||||
description: "Like local, but use Hugging Face Inference API (serverless) for running LLM inference.\nSee https://hf.co/docs/api-inference."
|
||||
providers:
|
||||
inference: remote::hf::serverless
|
||||
memory: meta-reference
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: conda
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
name: local-ollama
|
||||
distribution_spec:
|
||||
description: Like local, but use ollama for running LLM inference
|
||||
providers:
|
||||
inference: remote::ollama
|
||||
memory: meta-reference
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: conda
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
name: local-tgi
|
||||
distribution_spec:
|
||||
description: Like local, but use a TGI server for running LLM inference.
|
||||
providers:
|
||||
inference: remote::tgi
|
||||
memory: meta-reference
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: conda
|
||||
|
|
@ -1,11 +0,0 @@
|
|||
name: local-tgi-chroma
|
||||
distribution_spec:
|
||||
description: remote tgi inference + chromadb memory
|
||||
docker_image: null
|
||||
providers:
|
||||
inference: remote::tgi
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
memory: remote::chromadb
|
||||
telemetry: meta-reference
|
||||
image_type: docker
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
name: local-together
|
||||
distribution_spec:
|
||||
description: Use Together.ai for running LLM inference
|
||||
providers:
|
||||
inference: remote::together
|
||||
memory: meta-reference
|
||||
safety: remote::together
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: conda
|
||||
|
|
@ -1,50 +0,0 @@
|
|||
version: '2'
|
||||
built_at: '2024-10-08T17:40:45.325529'
|
||||
image_name: local
|
||||
docker_image: null
|
||||
conda_env: local
|
||||
apis:
|
||||
- shields
|
||||
- agents
|
||||
- models
|
||||
- memory
|
||||
- memory_banks
|
||||
- inference
|
||||
- safety
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: meta-reference
|
||||
provider_type: meta-reference
|
||||
config:
|
||||
model: Llama3.1-8B-Instruct
|
||||
quantization: null
|
||||
torch_seed: null
|
||||
max_seq_len: 4096
|
||||
max_batch_size: 1
|
||||
safety:
|
||||
- provider_id: meta-reference
|
||||
provider_type: meta-reference
|
||||
config:
|
||||
llama_guard_shield:
|
||||
model: Llama-Guard-3-1B
|
||||
excluded_categories: []
|
||||
disable_input_check: false
|
||||
disable_output_check: false
|
||||
prompt_guard_shield:
|
||||
model: Prompt-Guard-86M
|
||||
memory:
|
||||
- provider_id: meta-reference
|
||||
provider_type: meta-reference
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ~/.llama/runtime/kvstore.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: meta-reference
|
||||
config: {}
|
||||
|
|
@ -1,46 +0,0 @@
|
|||
version: '2'
|
||||
built_at: '2024-10-08T17:40:45.325529'
|
||||
image_name: local
|
||||
docker_image: null
|
||||
conda_env: local
|
||||
apis:
|
||||
- shields
|
||||
- agents
|
||||
- models
|
||||
- memory
|
||||
- memory_banks
|
||||
- inference
|
||||
- safety
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: tgi0
|
||||
provider_type: remote::tgi
|
||||
config:
|
||||
url: http://127.0.0.1:5009
|
||||
safety:
|
||||
- provider_id: meta-reference
|
||||
provider_type: meta-reference
|
||||
config:
|
||||
llama_guard_shield:
|
||||
model: Llama-Guard-3-1B
|
||||
excluded_categories: []
|
||||
disable_input_check: false
|
||||
disable_output_check: false
|
||||
prompt_guard_shield:
|
||||
model: Prompt-Guard-86M
|
||||
memory:
|
||||
- provider_id: meta-reference
|
||||
provider_type: meta-reference
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ~/.llama/runtime/kvstore.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: meta-reference
|
||||
config: {}
|
||||
Loading…
Add table
Add a link
Reference in a new issue