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

..

guided_decoding

[BUGFIX] Move scores to float32 in case of running xgrammar on cpu (#12152)

2025-01-19 11:12:05 +08:00

layers

[Model] Support for fairseq2 Llama (#11442)

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

model_loader

[Model] Support for fairseq2 Llama (#11442)

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

models

[Model] Support for fairseq2 Llama (#11442)

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

__init__.py

[Performance] Optimize e2e overheads: Reduce python allocations (#7162)

2024-08-08 21:34:28 -07:00

custom_op.py

[platform] support pytorch custom op pluggable (#11328)

2025-01-10 10:02:38 +00:00

parameter.py

[Misc][Quark] Upstream Quark format to VLLM (#10765)

2025-01-15 11:05:15 -05:00

pooling_metadata.py

[Model][Misc] Add e5-mistral-7b-instruct and Embedding API (#3734)

2024-05-11 11:30:37 -07:00

sampling_metadata.py

[Misc] typo find in sampling_metadata.py (#10740)

2024-11-29 05:17:57 +00:00

utils.py

[platforms] enable platform plugins (#11602)

2024-12-30 20:24:45 +08:00