Cody Yu ce532ff45c [Speculative decoding] Improve n-gram efficiency (#4724)

2024-05-13 15:00:13 -07:00

..

__init__.py

[Bugfix] Add __init__.py files for vllm/core/block/ and vllm/spec_decode/ (#3798)

2024-04-02 12:35:31 -07:00

batch_expansion.py

[Misc][Refactor] Introduce ExecuteModelData (#4540)

2024-05-03 17:47:07 -07:00

interfaces.py

[Misc][Refactor] Introduce ExecuteModelData (#4540)

2024-05-03 17:47:07 -07:00

metrics.py

[Speculative decoding 7/9] Speculative decoding end-to-end correctness tests. (#3951)

2024-04-23 08:02:36 +00:00

multi_step_worker.py

[Core] Fix circular reference which leaked llm instance in local dev env (#4737)

2024-05-10 23:54:32 +09:00

ngram_worker.py

[Speculative decoding] Improve n-gram efficiency (#4724)

2024-05-13 15:00:13 -07:00

spec_decode_worker.py

[Dynamic Spec Decoding] Auto-disable by the running queue size (#4592)

2024-05-08 21:44:00 +00:00

top1_proposer.py

[Speculative decoding] Improve n-gram efficiency (#4724)

2024-05-13 15:00:13 -07:00

util.py

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

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