Zhongkai Zhao 70885d707d [hotfix] Suport extra_kwargs in ShardConfig (#5031) ...

* [refactor]: replace inference args with extra_kwargs in ShardConfig

* modify shardconfig

* polish code

* fix policy bug in llama

* fix bug in auto policy

* remove setattr in ShardConfig

2023-11-10 10:49:50 +08:00

..

test_dynamic_batching

[hotfix] Suport extra_kwargs in ShardConfig (#5031)

2023-11-10 10:49:50 +08:00

_utils.py

[hotfix] Suport extra_kwargs in ShardConfig (#5031)

2023-11-10 10:49:50 +08:00

test_bloom_infer.py

[hotfix] Suport extra_kwargs in ShardConfig (#5031)

2023-11-10 10:49:50 +08:00

test_chatglm2_infer.py

[hotfix] Suport extra_kwargs in ShardConfig (#5031)

2023-11-10 10:49:50 +08:00

test_infer_engine.py

[hotfix] Suport extra_kwargs in ShardConfig (#5031)

2023-11-10 10:49:50 +08:00

test_kvcache_manager.py

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

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

test_llama2_infer.py

[hotfix] Suport extra_kwargs in ShardConfig (#5031)

2023-11-10 10:49:50 +08:00

test_llama_infer.py

[hotfix] Suport extra_kwargs in ShardConfig (#5031)

2023-11-10 10:49:50 +08:00

test_pipeline_infer.py

[format] applied code formatting on changed files in pull request 4926 (#5007)

2023-11-06 17:08:12 +08:00