Joe RundeandGitHub de4008e2ab [Bugfix][Core] Use torch.cuda.memory_stats() to profile peak memory usage (#9352) ...

Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>

2024-10-17 22:47:27 -04:00

..

__init__.py

[Speculative decoding 2/9] Multi-step worker for draft model (#2424)

2024-01-21 16:31:47 -08:00

test_encoder_decoder_model_runner.py

[Core] Factor out common code in SequenceData and Sequence (#8675)

2024-09-21 02:30:39 +00:00

test_model_input.py

[Core] Add AttentionState abstraction (#7663)

2024-08-20 18:50:45 +00:00

test_model_runner.py

[Core] Factor out common code in SequenceData and Sequence (#8675)

2024-09-21 02:30:39 +00:00

test_profile.py

[Bugfix][Core] Use torch.cuda.memory_stats() to profile peak memory usage (#9352)

2024-10-17 22:47:27 -04:00

test_swap.py

[Core] Pipeline Parallel Support (#4412)

2024-07-02 10:58:08 -07:00