Kuntai Du 81ede99ca4

[Core] Deprecating block manager v1 and make block manager v2 default (#8704) ...

Removing the block manager v1. This is the initial piece of prefix-caching-centric design. In order to achieve prefix-caching-centric design, we need to simplify the code path so that we only use v2 block manager (which has much higher performance on prefix caching).

2024-10-17 11:38:15 -05:00

..

adding_model.rst

[Misc] Collect model support info in a single process per model (#9233)

2024-10-11 11:08:11 +00:00

enabling_multimodal_inputs.rst

[VLM][Core] Support profiling with multiple multi-modal inputs per prompt (#7126)

2024-08-14 17:55:42 +00:00

engine_args.rst

[Doc][CI/Build] Update docs and tests to use vllm serve (#6431)

2024-07-17 07:43:21 +00:00

lora.rst

[Core] Support Lora lineage and base model metadata management (#6315)

2024-09-20 06:20:56 +00:00

performance.rst

[Doc] Compatibility matrix for mutual exclusive features (#8512)

2024-10-11 11:18:50 -07:00

spec_decode.rst

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

supported_models.rst

[Model][Bugfix] Add FATReLU activation and support for openbmb/MiniCPM-S-1B-sft (#9396)

2024-10-16 16:40:24 +00:00

vlm.rst

[Misc] Consolidate example usage of OpenAI client for multimodal models (#9412)

2024-10-16 11:20:51 +00:00