3 people fd95e026e0 [Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942) ...

Co-authored-by: Andrew Feldman <afeld2012@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>

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

..

__init__.py

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

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

block_table.py

[Misc] Small perf improvements (#6520)

2024-07-19 12:10:56 -07:00

common.py

[Core] Optimize block_manager_v2 vs block_manager_v1 (to make V2 default) (#5602)

2024-07-01 20:10:37 -07:00

cpu_gpu_block_allocator.py

[Core] Optimize block_manager_v2 vs block_manager_v1 (to make V2 default) (#5602)

2024-07-01 20:10:37 -07:00

interfaces.py

[Core] Optimize block_manager_v2 vs block_manager_v1 (to make V2 default) (#5602)

2024-07-01 20:10:37 -07:00

naive_block.py

[Core] Optimize block_manager_v2 vs block_manager_v1 (to make V2 default) (#5602)

2024-07-01 20:10:37 -07:00

prefix_caching_block.py

[Misc] Small perf improvements (#6520)

2024-07-19 12:10:56 -07:00

utils.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