mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-16 14:38:00 +00:00
3 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Ashwin Bharambe
|
7f834339ba
|
chore(misc): make tests and starter faster (#3042)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 9s
Python Package Build Test / build (3.12) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 12s
Test Llama Stack Build / generate-matrix (push) Successful in 11s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 14s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 22s
Test External API and Providers / test-external (venv) (push) Failing after 14s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 15s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 22s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 14s
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Test Llama Stack Build / build-single-provider (push) Failing after 13s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 18s
Unit Tests / unit-tests (3.12) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.12, remote::qdrant) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.13, remote::weaviate) (push) Failing after 10s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 11s
Vector IO Integration Tests / test-matrix (3.12, remote::weaviate) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.13, remote::qdrant) (push) Failing after 18s
Test Llama Stack Build / build (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 20s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 16s
Python Package Build Test / build (3.13) (push) Failing after 53s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 59s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 1m1s
Update ReadTheDocs / update-readthedocs (push) Failing after 1m6s
Pre-commit / pre-commit (push) Successful in 1m53s
A bunch of miscellaneous cleanup focusing on tests, but ended up speeding up starter distro substantially. - Pulled llama stack client init for tests into `pytest_sessionstart` so it does not clobber output - Profiling of that told me where we were doing lots of heavy imports for starter, so lazied them - starter now starts 20seconds+ faster on my Mac - A few other smallish refactors for `compat_client` |
||
Nehanth Narendrula
|
cf73146132
|
feat: Enable DPO training with HuggingFace inline provider (#2825)
Some checks failed
Integration Tests / discover-tests (push) Has been skipped
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 7s
Integration Tests / record-tests (push) Has been skipped
Integration Tests / run-tests (push) Has been skipped
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 22s
Python Package Build Test / build (3.13) (push) Failing after 16s
Test Llama Stack Build / generate-matrix (push) Successful in 19s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 21s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 31s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 32s
Test External API and Providers / test-external (venv) (push) Failing after 32s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 36s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 39s
Update ReadTheDocs / update-readthedocs (push) Failing after 31s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 42s
Test Llama Stack Build / build-single-provider (push) Failing after 37s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Failing after 35s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 37s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 40s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 42s
Unit Tests / unit-tests (3.12) (push) Failing after 36s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 40s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 45s
Test Llama Stack Build / build (push) Failing after 6s
Python Package Build Test / build (3.12) (push) Failing after 1m1s
Unit Tests / unit-tests (3.13) (push) Failing after 1m0s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 1m6s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 1m8s
Pre-commit / pre-commit (push) Successful in 1m50s
What does this PR do? This PR adds support for Direct Preference Optimization (DPO) training via the existing HuggingFace inline provider. It introduces a new DPO training recipe, config schema updates, dataset integration, and end-to-end testing to support preference-based fine-tuning with TRL. Test Plan Added integration test: tests/integration/post_training/test_post_training.py::TestPostTraining::test_preference_optimize Ran tests on both CPU and CUDA environments --------- Co-authored-by: Ubuntu <ubuntu@ip-172-31-43-83.ec2.internal> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com> |
||
Charlie Doern
|
f02f7b28c1
|
feat: add huggingface post_training impl (#2132)
# What does this PR do? adds an inline HF SFTTrainer provider. Alongside touchtune -- this is a super popular option for running training jobs. The config allows a user to specify some key fields such as a model, chat_template, device, etc the provider comes with one recipe `finetune_single_device` which works both with and without LoRA. any model that is a valid HF identifier can be given and the model will be pulled. this has been tested so far with CPU and MPS device types, but should be compatible with CUDA out of the box The provider processes the given dataset into the proper format, establishes the various steps per epoch, steps per save, steps per eval, sets a sane SFTConfig, and runs n_epochs of training if checkpoint_dir is none, no model is saved. If there is a checkpoint dir, a model is saved every `save_steps` and at the end of training. ## Test Plan re-enabled post_training integration test suite with a singular test that loads the simpleqa dataset: https://huggingface.co/datasets/llamastack/simpleqa and a tiny granite model: https://huggingface.co/ibm-granite/granite-3.3-2b-instruct. The test now uses the llama stack client and the proper post_training API runs one step with a batch_size of 1. This test runs on CPU on the Ubuntu runner so it needs to be a small batch and a single step. [//]: # (## Documentation) --------- Signed-off-by: Charlie Doern <cdoern@redhat.com> |