Martin Gleize bbe5f9de7d [Model] Support for fairseq2 Llama (#11442) ...

Signed-off-by: Martin Gleize <mgleize@meta.com>
Co-authored-by: mgleize user <mgleize@a100-st-p4de24xlarge-4.fair-a100.hpcaas>

2025-01-19 10:40:40 -08:00

..

decoder_only

[V1] Add V1 support of Qwen2-VL (#12128)

2025-01-19 19:52:13 +08:00

embedding

[Bugfix] Fix RobertaModel loading (#11940)

2025-01-11 14:05:09 +00:00

encoder_decoder

[Model] Whisper model implementation (#11280)

2025-01-03 16:39:19 +08:00

fixtures

[CI/Build] Update pixtral tests to use JSON (#8436)

2024-09-13 03:47:52 +00:00

multimodal

[Model] Port deepseek-vl2 processor, remove dependency (#12169)

2025-01-18 13:59:39 +08:00

__init__.py

[CI/Build] Move test_utils.py to tests/utils.py (#4425)

2024-05-13 23:50:09 +09:00

registry.py

[Model] Support for fairseq2 Llama (#11442)

2025-01-19 10:40:40 -08:00

test_initialization.py

[Model] Initialize support for Deepseek-VL2 models (#11578)

2025-01-12 00:17:24 -08:00

test_oot_registration.py

[Frontend] Separate pooling APIs in offline inference (#11129)

2024-12-13 10:40:07 +00:00

test_registry.py

[Model] Automatic conversion of classification and reward models (#11469)

2024-12-24 18:22:22 +00:00

utils.py

[CI/Build] Update CPU tests to include all "standard" tests (#5481)

2024-11-08 23:30:04 +08:00