zhaoyang-star 9090bf02e7

Support FP8-E5M2 KV Cache (#2279) ...

Co-authored-by: zhaoyang <zhao.yang16@zte.com.cn>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>

2024-01-28 16:43:54 -08:00

..

async_engine

[Experimental] Add multi-LoRA support (#1804)

2024-01-23 15:26:37 -08:00

distributed

Implement custom all reduce kernels (#2192)

2024-01-27 12:46:35 -08:00

engine

Migrate linter from pylint to ruff (#1665)

2023-11-20 11:58:01 -08:00

entrypoints

Support Batch Completion in Server (#2529)

2024-01-24 17:11:07 -08:00

kernels

Support FP8-E5M2 KV Cache (#2279)

2024-01-28 16:43:54 -08:00

lora

[Experimental] Add multi-LoRA support (#1804)

2024-01-23 15:26:37 -08:00

models

Add StableLM3B model (#2372)

2024-01-16 20:32:40 -08:00

prefix_caching

[Experimental] Prefix Caching Support (#1669)

2024-01-17 16:32:10 -08:00

prompts

[BugFix] Fix input positions for long context with sliding window (#2088)

2023-12-13 12:28:13 -08:00

samplers

[Experimental] Add multi-LoRA support (#1804)

2024-01-23 15:26:37 -08:00

worker

[Experimental] Add multi-LoRA support (#1804)

2024-01-23 15:26:37 -08:00

__init__.py

[Small] Formatter only checks lints in changed files (#1528)

2023-10-31 15:39:38 -07:00

conftest.py

[BUGFIX] Fix the path of test prompts (#2273)

2023-12-26 10:37:21 -08:00

test_regression.py

[Bugfix] fix crash if max_tokens=None (#2570)

2024-01-23 22:38:55 -08:00

test_sampling_params.py

[Bugfix] fix crash if max_tokens=None (#2570)

2024-01-23 22:38:55 -08:00