ColossalAI/colossalai
Bin Jia b6696beb04
[Pipeline Inference] Merge pp with tp (#4993)
* refactor pipeline into new CaiInferEngine

* updata llama modeling forward

* merge tp with pp

* update docstring

* optimize test workflow and example

* fix typo

* add assert and todo
2023-11-01 12:46:21 +08:00
..
_C [setup] support pre-build and jit-build of cuda kernels (#2374) 2023-01-06 20:50:26 +08:00
_analyzer [misc] update pre-commit and run all files (#4752) 2023-09-19 14:20:26 +08:00
amp [feature] Add clip_grad_norm for hybrid_parallel_plugin (#4837) 2023-10-12 11:32:37 +08:00
auto_parallel [misc] update pre-commit and run all files (#4752) 2023-09-19 14:20:26 +08:00
autochunk [misc] update pre-commit and run all files (#4752) 2023-09-19 14:20:26 +08:00
booster [hotfix] fix the bug of repeatedly storing param group (#4951) 2023-10-31 14:48:01 +08:00
checkpoint_io [checkpointio] hotfix torch 2.0 compatibility (#4824) 2023-10-07 10:45:52 +08:00
cli [bug] Fix the version check bug in colossalai run when generating the cmd. (#4713) 2023-09-22 10:50:47 +08:00
cluster [hotfix] Fix the bug where process groups were not being properly released. (#4940) 2023-10-31 14:47:30 +08:00
context [misc] update pre-commit and run all files (#4752) 2023-09-19 14:20:26 +08:00
device [misc] update pre-commit and run all files (#4752) 2023-09-19 14:20:26 +08:00
fx [misc] update pre-commit and run all files (#4752) 2023-09-19 14:20:26 +08:00
inference [Pipeline Inference] Merge pp with tp (#4993) 2023-11-01 12:46:21 +08:00
interface [lazy] support from_pretrained (#4801) 2023-09-26 11:04:11 +08:00
kernel [Kernels]Updated Triton kernels into 2.1.0 and adding flash-decoding for llama token attention (#4965) 2023-10-30 14:04:37 +08:00
lazy [doc] add lazy init docs (#4808) 2023-09-27 10:24:04 +08:00
legacy [hotfix] fix torch 2.0 compatibility (#4936) 2023-10-18 11:05:25 +08:00
logging [misc] update pre-commit and run all files (#4752) 2023-09-19 14:20:26 +08:00
nn [test] add no master test for low level zero plugin (#4934) 2023-10-18 11:41:23 +08:00
pipeline [Pipeline inference] Combine kvcache with pipeline inference (#4938) 2023-10-27 16:19:54 +08:00
shardformer [Pipeline inference] Combine kvcache with pipeline inference (#4938) 2023-10-27 16:19:54 +08:00
tensor [hotfix] Fix the bug where process groups were not being properly released. (#4940) 2023-10-31 14:47:30 +08:00
testing [test] merge old components to test to model zoo (#4945) 2023-10-20 10:35:08 +08:00
utils [misc] update pre-commit and run all files (#4752) 2023-09-19 14:20:26 +08:00
zero [gemini] support gradient accumulation (#4869) 2023-10-17 14:07:21 +08:00
__init__.py [misc] update pre-commit and run all files (#4752) 2023-09-19 14:20:26 +08:00
initialize.py [misc] update pre-commit and run all files (#4752) 2023-09-19 14:20:26 +08:00