phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions
llama-stack/llama_stack/apis
History
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
..
agents migrate memory banks to Resource and new registration (#411) 2024-11-11 17:10:44 -08:00
batch_inference Remove "routing_table" and "routing_key" concepts for the user (#201) 2024-10-10 10:24:13 -07:00
common [Evals API][4/n] evals with generation meta-reference impl (#303) 2024-10-25 13:12:39 -07:00
datasetio migrate dataset to resource (#420) 2024-11-11 17:14:41 -08:00
datasets change schema -> dataset_schema for register_dataset api (#443) 2024-11-13 11:17:46 -05:00
eval [Evals API][11/n] huggingface dataset provider + mmlu scoring fn (#392) 2024-11-11 14:49:50 -05:00
eval_tasks Remove the "ShieldType" concept (#430) 2024-11-12 12:37:24 -08:00
inference Inference to use provider resource id to register and validate (#428) 2024-11-12 20:02:00 -08:00
inspect Remove "routing_table" and "routing_key" concepts for the user (#201) 2024-10-10 10:24:13 -07:00
memory migrate memory banks to Resource and new registration (#411) 2024-11-11 17:10:44 -08:00
memory_banks Remove the "ShieldType" concept (#430) 2024-11-12 12:37:24 -08:00
models Support model resource updates and deletes (#452) 2024-11-13 21:55:41 -08:00
post_training [Evals API][4/n] evals with generation meta-reference impl (#303) 2024-10-25 13:12:39 -07:00
safety Remove the "ShieldType" concept (#430) 2024-11-12 12:37:24 -08:00
scoring migrate scoring fns to resource (#422) 2024-11-11 17:28:48 -08:00
scoring_functions Remove the "ShieldType" concept (#430) 2024-11-12 12:37:24 -08:00
shields Remove the "ShieldType" concept (#430) 2024-11-12 12:37:24 -08:00
synthetic_data_generation [Evals API][4/n] evals with generation meta-reference impl (#303) 2024-10-25 13:12:39 -07:00
telemetry Remove "routing_table" and "routing_key" concepts for the user (#201) 2024-10-10 10:24:13 -07:00
__init__.py API Updates (#73) 2024-09-17 19:51:35 -07:00
resource.py Enable sane naming of registered objects with defaults (#429) 2024-11-12 11:18:05 -08:00