github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-05-08 00:18:25 +00:00
Code Issues Packages Projects Releases Wiki Activity
22ce873c3f
ColossalAI/colossalai
History
Haze188 22ce873c3f
[Shardformer] Add parallel output for shardformer models(bloom, falcon) () 
* [pre-commit.ci] auto fixes from pre-commit.com hooks

* add parallel cross entropy output for falcon model & fix some typos in bloom.py

* fix module name error, self.model -> self.transformers in bloom, falcon model

* Fix the overflow bug of distributed cross entropy loss function when training with fp16

* add dtype to parallel cross entropy loss function

* fix dtype related typos adn prettify the loss.py

* fix grad dtype and update dtype mismatch error

* fix typo bugs
2024-05-21 11:07:13 +08:00
..
_analyzer [hotfix] Fix examples no pad token & auto parallel codegen bug; () 2024-04-18 18:15:50 +08:00
_C [setup] support pre-build and jit-build of cuda kernels () 2023-01-06 20:50:26 +08:00
accelerator [hotfix] fix typo change MoECheckpintIO to MoECheckpointIO () 2024-03-05 21:52:30 +08:00
amp [npu] change device to accelerator api () 2024-01-09 10:20:05 +08:00
auto_parallel [misc] refactor launch API and tensor constructor () 2024-04-29 10:40:11 +08:00
autochunk [hotfix] Fix examples no pad token & auto parallel codegen bug; () 2024-04-18 18:15:50 +08:00
booster [Feature] Distributed optimizers: Lamb, Galore, CAME and Adafactor () 2024-05-14 13:52:45 +08:00
checkpoint_io [lora] add lora APIs for booster, support lora for TorchDDP () 2024-04-28 10:51:27 +08:00
cli [devops] fix extention building () 2024-03-05 15:35:54 +08:00
cluster [Feature] Distributed optimizers: Lamb, Galore, CAME and Adafactor () 2024-05-14 13:52:45 +08:00
context [Fix]: implement thread-safety singleton to avoid deadlock for very large-scale training scenarios () 2024-04-25 14:45:52 +08:00
device [Feature] Distributed optimizers: Lamb, Galore, CAME and Adafactor () 2024-05-14 13:52:45 +08:00
fx [hotfix] Fix examples no pad token & auto parallel codegen bug; () 2024-04-18 18:15:50 +08:00
inference [misc] refactor launch API and tensor constructor () 2024-04-29 10:40:11 +08:00
interface [Feature] Distributed optimizers: Lamb, Galore, CAME and Adafactor () 2024-05-14 13:52:45 +08:00
kernel [coloattention]modify coloattention () 2024-04-25 10:47:14 +08:00
lazy [lazy] fix lazy cls init () 2024-05-17 18:18:59 +08:00
legacy [hotfix] fix inference typo () 2024-05-13 21:06:44 +08:00
logging [misc] update pre-commit and run all files () 2023-09-19 14:20:26 +08:00
moe [hotfix] fix typo change MoECheckpintIO to MoECheckpointIO () 2024-03-05 21:52:30 +08:00
nn [Feature] Distributed optimizers: Lamb, Galore, CAME and Adafactor () 2024-05-14 13:52:45 +08:00
pipeline [LowLevelZero] low level zero support lora () 2024-04-28 10:51:27 +08:00
quantization [Feature] qlora support () 2024-04-28 10:51:27 +08:00
shardformer [Shardformer] Add parallel output for shardformer models(bloom, falcon) () 2024-05-21 11:07:13 +08:00
tensor [Feature] Distributed optimizers: Lamb, Galore, CAME and Adafactor () 2024-05-14 13:52:45 +08:00
testing [shardformer] refactor embedding resize () 2024-04-18 16:10:18 +08:00
utils Merge pull request from hpcaitech/feature/npu 2024-01-29 13:49:39 +08:00
zero [Feature] Distributed optimizers: Lamb, Galore, CAME and Adafactor () 2024-05-14 13:52:45 +08:00
__init__.py [devops] remove post commit ci () 2024-04-08 15:09:40 +08:00
initialize.py [misc] refactor launch API and tensor constructor () 2024-04-29 10:40:11 +08:00