phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions
508 commits 21 branches 64 tags 62 MiB
Commit graph

3 commits

Author SHA1 Message Date
Dinesh Yeduguru
0850ad656a
unregister for memory banks and remove update API (#458) 
The semantics of an Update on resources is very tricky to reason about
especially for memory banks and models. The best way to go forward here
is for the user to unregister and register a new resource. We don't have
a compelling reason to support update APIs.


Tests:
pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m
"chroma" --env CHROMA_HOST=localhost --env CHROMA_PORT=8000

pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m
"pgvector" --env PGVECTOR_DB=postgres --env PGVECTOR_USER=postgres --env
PGVECTOR_PASSWORD=mysecretpassword --env PGVECTOR_HOST=0.0.0.0

$CONDA_PREFIX/bin/pytest -v -s -m "ollama"
llama_stack/providers/tests/inference/test_model_registration.py

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
 2024-11-14 17:12:11 -08:00
Dinesh Yeduguru
efe791bab7
Support model resource updates and deletes (#452) 
# What does this PR do?
* Changes the registry to store only one RoutableObject per identifier.
Before it was a list, which is not really required.
* Adds impl for updates and deletes
* Updates routing table to handle updates correctly



## Test Plan
```
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier             | provider_id   | provider_resource_id               | metadata   |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0   | fireworks/llama-v3p1-405b-instruct | {}         |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct   | fireworks-0   | fireworks/llama-v3p1-8b-instruct   | {}         |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct   | fireworks-0   | fireworks/llama-v3p2-1b-instruct   | {}         |
+------------------------+---------------+------------------------------------+------------+
❯ llama-stack-client models register dineshyv-model --provider-model-id=fireworks/llama-v3p1-70b-instruct
Successfully registered model dineshyv-model
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier             | provider_id   | provider_resource_id               | metadata   |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0   | fireworks/llama-v3p1-405b-instruct | {}         |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct   | fireworks-0   | fireworks/llama-v3p1-8b-instruct   | {}         |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct   | fireworks-0   | fireworks/llama-v3p2-1b-instruct   | {}         |
+------------------------+---------------+------------------------------------+------------+
| dineshyv-model         | fireworks-0   | fireworks/llama-v3p1-70b-instruct  | {}         |
+------------------------+---------------+------------------------------------+------------+
❯ llama-stack-client models update dineshyv-model --provider-model-id=fireworks/llama-v3p1-405b-instruct
Successfully updated model dineshyv-model
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier             | provider_id   | provider_resource_id               | metadata   |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0   | fireworks/llama-v3p1-405b-instruct | {}         |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct   | fireworks-0   | fireworks/llama-v3p1-8b-instruct   | {}         |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct   | fireworks-0   | fireworks/llama-v3p2-1b-instruct   | {}         |
+------------------------+---------------+------------------------------------+------------+
| dineshyv-model         | fireworks-0   | fireworks/llama-v3p1-405b-instruct | {}         |
+------------------------+---------------+------------------------------------+------------+
llama-stack-client models delete dineshyv-model
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier             | provider_id   | provider_resource_id               | metadata   |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0   | fireworks/llama-v3p1-405b-instruct | {}         |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct   | fireworks-0   | fireworks/llama-v3p1-8b-instruct   | {}         |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct   | fireworks-0   | fireworks/llama-v3p2-1b-instruct   | {}         |
+------------------------+---------------+------------------------------------+------------+

```

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
 2024-11-13 21:55:41 -08:00
Dinesh Yeduguru
787e2034b7
model registration in ollama and vllm check against the available models in the provider (#446) 
tests:
pytest -v -s -m "ollama"
llama_stack/providers/tests/inference/test_text_inference.py

pytest -v -s -m vllm_remote
llama_stack/providers/tests/inference/test_text_inference.py --env
VLLM_URL="http://localhost:9798/v1"

---------
 2024-11-13 13:04:06 -08:00