maximzubkov 521b35f799 Support Microsoft Phi 1.5 (#1664)		2023-11-16 14:28:39 -08:00
..
async_engine	Implement prompt logprobs & Batched topk for computing logprobs (#1328)	2023-10-16 10:56:50 -07:00
distributed	TP/quantization/weight loading refactor part 1 - Simplify parallel linear logic (#1181)	2023-10-02 15:36:09 -07:00
engine	TP/quantization/weight loading refactor part 1 - Simplify parallel linear logic (#1181)	2023-10-02 15:36:09 -07:00
kernels	Fix integer overflows in attention & cache ops (#1514)	2023-10-31 15:19:30 -07:00
models	Support Microsoft Phi 1.5 (#1664)	2023-11-16 14:28:39 -08:00
samplers	Added logits processor API to sampling params (#1469)	2023-11-03 14:12:15 -07:00
worker	Fix input_metadata.selected_token_indices in worker prepare_inputs (#1546)	2023-11-08 14:19:12 -08:00
__init__.py	[Small] Formatter only checks lints in changed files (#1528)	2023-10-31 15:39:38 -07:00
conftest.py	Implement prompt logprobs & Batched topk for computing logprobs (#1328)	2023-10-16 10:56:50 -07:00
test_regression.py	[Minor] Fix duplication of ignored seq group in engine step (#1666)	2023-11-16 13:11:41 -08:00