botbw 8e718a1421 [gemini] fixes for benchmarking (#5847) ...

* [gemini] fix missing return

* [gemini] fix missing arg pass

* [gemini] use gather tensor instead of list

* [test] enable flash attention for benchmark by default

* [test] enable flash attention for benchmark by default

---------

Co-authored-by: genghaozhe <939857490@qq.com>

2024-06-26 15:52:09 +08:00

..

__init__.py

[misc] update pre-commit and run all files (#4752)

2023-09-19 14:20:26 +08:00

chunk.py

[gemini] fixes for benchmarking (#5847)

2024-06-26 15:52:09 +08:00

manager.py

[gemini] fixes for benchmarking (#5847)

2024-06-26 15:52:09 +08:00

search_utils.py

[misc] update pre-commit and run all files (#4752)

2023-09-19 14:20:26 +08:00

utils.py

[Gemini] Use async stream to prefetch and h2d data moving (#5781)

2024-06-12 15:48:52 +08:00