ColossalAI/tests
Yuanheng Zhao 17cfa57140
[infer] Add Bloom inference policy and replaced methods (#4512)
* add bloom inference methods and policy

* enable pass BatchInferState from model forward

* revise bloom infer layers/policies

* add engine for inference (draft)

* add test for bloom infer

* fix bloom infer policy and flow

* revise bloom test

* fix bloom file path

* remove unused codes

* fix bloom modeling

* fix dir typo

* fix trivial

* fix policy

* clean pr

* trivial fix
2023-08-30 17:50:41 +08:00
..
components_to_test [CI] fix typo with tests/ etc. (#3727) 2023-05-11 16:30:58 +08:00
kit [shardformer]update t5 tests for using all optimizations. (#4407) 2023-08-15 23:25:14 +08:00
test_amp [test] refactor tests with spawn (#3452) 2023-04-06 14:51:35 +08:00
test_analyzer [devops] update torch version of CI (#3725) 2023-05-15 17:20:56 +08:00
test_auto_parallel [gemini] fix argument naming during chunk configuration searching 2023-06-25 13:34:15 +08:00
test_autochunk [test] fixed tests failed due to dtensor change (#4082) 2023-07-04 16:05:01 +08:00
test_booster [Shardformer] Merge flash attention branch to pipeline branch (#4362) 2023-08-15 23:25:14 +08:00
test_checkpoint_io [zero] support shard optimizer state dict of zero (#4194) 2023-07-31 22:13:29 +08:00
test_cluster [cluster] add process group mesh (#4039) 2023-08-15 23:25:14 +08:00
test_comm [test] refactor tests with spawn (#3452) 2023-04-06 14:51:35 +08:00
test_config [pipeline] refactor the pipeline module (#1087) 2022-06-10 11:27:38 +08:00
test_context [test] refactor tests with spawn (#3452) 2023-04-06 14:51:35 +08:00
test_data [test] refactor tests with spawn (#3452) 2023-04-06 14:51:35 +08:00
test_data_pipeline_tensor_parallel [CI] fix typo with tests/ etc. (#3727) 2023-05-11 16:30:58 +08:00
test_ddp [test] refactor tests with spawn (#3452) 2023-04-06 14:51:35 +08:00
test_device [format] applied code formatting on changed files in pull request 4152 (#4157) 2023-07-04 16:07:47 +08:00
test_engine [test] refactor tests with spawn (#3452) 2023-04-06 14:51:35 +08:00
test_fx [misc] resolve code factor issues (#4433) 2023-08-15 23:25:14 +08:00
test_infer [infer] Add Bloom inference policy and replaced methods (#4512) 2023-08-30 17:50:41 +08:00
test_infer_ops [Bug FIx] import llama context ops fix (#4524) 2023-08-28 13:41:57 +08:00
test_layers [CI] fix typo with tests/ etc. (#3727) 2023-05-11 16:30:58 +08:00
test_lazy [test] skip some not compatible models 2023-08-15 23:25:14 +08:00
test_moe [CI] fix typo with tests/ etc. (#3727) 2023-05-11 16:30:58 +08:00
test_ops [test] refactor tests with spawn (#3452) 2023-04-06 14:51:35 +08:00
test_optimizer [bf16] add bf16 support (#3882) 2023-06-05 15:58:31 +08:00
test_pipeline [format] applied code formatting on changed files in pull request 4441 (#4445) 2023-08-16 10:47:23 +08:00
test_shardformer [misc] resolve code factor issues (#4433) 2023-08-15 23:25:14 +08:00
test_tensor [test] fixed tests failed due to dtensor change (#4082) 2023-07-04 16:05:01 +08:00
test_trainer [CI] fix typo with tests/ etc. (#3727) 2023-05-11 16:30:58 +08:00
test_utils [shardformer] update shardformer to use flash attention 2 (#4392) 2023-08-15 23:25:14 +08:00
test_zero [hotfix] fix unsafe async comm in zero (#4404) 2023-08-11 15:09:24 +08:00
__init__.py [zero] Update sharded model v2 using sharded param v2 (#323) 2022-03-11 15:50:28 +08:00