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

..

block

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

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

__init__.py

[Tests] Add block manager and scheduler tests (#3108)

2024-03-05 18:23:34 -08:00

test_chunked_prefill_scheduler.py

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

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

test_num_computed_tokens_update.py

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

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

test_scheduler_encoder_decoder.py

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)

2024-08-06 16:51:47 -04:00

test_scheduler.py

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

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

test_serialization.py

[Core] Optimize SPMD architecture with delta + serialization optimization (#7109)

2024-08-18 17:57:20 -07:00

utils.py

[core] remove beam search from the core (#9105)

2024-10-07 05:47:04 +00:00