Alexander Matveev e02ac55617 [Performance] Optimize e2e overheads: Reduce python allocations (#7162)

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

..

backends

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

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

ops

[Bugfix] Allow vllm to still work if triton is not installed. (#6786)

2024-07-29 14:51:27 -07:00

__init__.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

layer.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

selector.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