VED d0d26d5064 feat: Add GDPO Support (#3353) ...

* gdpo support - test left

* lint

* fixxes for vllm serv

* test advantages

* docss

* lint

* lint =

* gdpo simple + lint

* lint nit

* example

* lint

* trl 0.27.0

* blocklist

* test assert rmv

* add validation check for GDPO + sum_then_normalize

---------

Co-authored-by: Wing Lian <wing@axolotl.ai>

2026-01-21 17:22:45 -05:00

..

patched

Distributed/ND-Parallel (#2977)

2025-07-31 15:25:02 -04:00

solo

feat: Add GDPO Support (#3353)

2026-01-21 17:22:45 -05:00

__init__.py

Attempt to run multigpu in PR CI for now to ensure it works (#1815) [skip ci]

2024-08-09 11:50:13 -04:00

test_dist_muon_fsdp2.py

Distributed Muon Optimizer (#3264)

2025-12-19 10:43:47 -05:00

test_eval.py

Add ruff, remove black, isort, flake8, pylint (#3092)

2025-08-23 23:37:33 -04:00

test_fp8_fsdp2.py

Add ruff, remove black, isort, flake8, pylint (#3092)

2025-08-23 23:37:33 -04:00

test_fsdp1.py

Add ruff, remove black, isort, flake8, pylint (#3092)

2025-08-23 23:37:33 -04:00

test_fsdp2.py

Add ruff, remove black, isort, flake8, pylint (#3092)

2025-08-23 23:37:33 -04:00

test_gemma3.py

Add ruff, remove black, isort, flake8, pylint (#3092)

2025-08-23 23:37:33 -04:00

test_llama.py

upgrade transformers==4.57.1 and peft==0.23.1 (#3214)

2025-10-14 15:54:05 -04:00

test_locking.py

Data loader refactor (#2707)

2025-06-10 19:53:07 -04:00

test_ray.py

When using Ray use prepare for dataloader fixes (#3198)

2025-10-08 10:43:41 -04:00

test_tp.py

Add ruff, remove black, isort, flake8, pylint (#3092)

2025-08-23 23:37:33 -04:00