ColossalAI/colossalai
Yuanheng f8598e3ec5 [Fix] Llama Modeling Control with Spec-Dec (#5580)
- fix ref before asgmt
- fall back to use triton kernels when using spec-dec
2024-04-10 18:19:44 +08:00
..
_analyzer [hotfix] quick fixes to make legacy tutorials runnable (#5559) 2024-04-07 12:06:27 +08:00
_C
accelerator [hotfix] fix typo change MoECheckpintIO to MoECheckpointIO (#5335) 2024-03-05 21:52:30 +08:00
amp [npu] change device to accelerator api (#5239) 2024-01-09 10:20:05 +08:00
auto_parallel [hotfix] Fix wrong import in meta_registry (#5392) 2024-02-20 19:24:43 +08:00
autochunk
booster [devops] remove post commit ci (#5566) 2024-04-08 15:09:40 +08:00
checkpoint_io [devops] remove post commit ci (#5566) 2024-04-08 15:09:40 +08:00
cli [devops] fix extention building (#5427) 2024-03-05 15:35:54 +08:00
cluster [devops] remove post commit ci (#5566) 2024-04-08 15:09:40 +08:00
context
device
fx
inference [Fix] Llama Modeling Control with Spec-Dec (#5580) 2024-04-10 18:19:44 +08:00
interface
kernel [Inference/SpecDec] Add Speculative Decoding Implementation (#5423) 2024-04-10 11:07:52 +08:00
lazy
legacy [Fix] resolve conflicts of merging main 2024-04-08 16:21:47 +08:00
logging
moe [hotfix] fix typo change MoECheckpintIO to MoECheckpointIO (#5335) 2024-03-05 21:52:30 +08:00
nn [hotfix] quick fixes to make legacy tutorials runnable (#5559) 2024-04-07 12:06:27 +08:00
pipeline [shardformer, pipeline] add gradient_checkpointing_ratio and heterogenous shard policy for llama (#5508) 2024-04-01 11:34:58 +08:00
shardformer [Fix] resolve conflicts of merging main 2024-04-08 16:21:47 +08:00
tensor [devops] remove post commit ci (#5566) 2024-04-08 15:09:40 +08:00
testing [shardformer] update colo attention to support custom mask (#5510) 2024-03-27 11:19:32 +08:00
utils Merge pull request #5310 from hpcaitech/feature/npu 2024-01-29 13:49:39 +08:00
zero [devops] remove post commit ci (#5566) 2024-04-08 15:09:40 +08:00
__init__.py [devops] remove post commit ci (#5566) 2024-04-08 15:09:40 +08:00
initialize.py [npu] change device to accelerator api (#5239) 2024-01-09 10:20:05 +08:00