mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2026-07-17 02:00:25 +00:00
7bb7e80476
* add reward related function * add simple grpo * update grpo * polish * modify data loader * grpo consumer * update loss * update reward fn * update example * update loader * add algo selection * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add save * update select algo * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update grpo * update reward fn * update reward * fix reward score * add response length * detach * fix tp bug * fix consumer * convert to 8 generation * print results * setup update * fix transformers backend * [Feature] Support Distributed LogProb for GRPO Training (#6247) * [fix] fix qwen VocabParallelLMHead1D and gather output * fix tp bug * fix consumer * [feat] Support Distributed LogProb for GRPO Training * [fix] fix loss func * [fix] fix log prob plugin * [fix] fix qwen modeling param * [fix] rm comments * [fix] rm hard-code;fix non-dist version * [fix] fix test file param name and benchmark tp gather output=True/False * [fix] rm non-dist version in dist log prob * [fix] fix comments * [fix] fix dis log prob plugin * [fix] fix test case * [fix] fix qwen VocabParallelLMHead1D and gather output * [fix] fix DistLogProb comments * [fix] restore tp size * [fix] fix comments * [fix] fix comment; fix LogSoftmax usage --------- Co-authored-by: Tong Li <tong.li35271158@gmail.com> * fix vllm * fix logprob, add filtering, temperature annealing, lr descent * simplify vllm preprocessing input ids * update logging * [feat] add microbatch forwarding (#6251) * add microbatch forwarding * fix forward microbatch * fix producer OOM * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * change project name * fix temperature annealing * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * address conversation --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * [Distributed RLHF] Integration of PP (#6257) * update help information * update style * fix * minor fix * support PP training * add pp support * remove unused code * address conversation --------- Co-authored-by: Tong Li <tong.li35271158@gmail.com> * [hot-fix] Fix memory leakage bug, support TP+PP (#6258) * update help information * update style * fix * minor fix * support PP training * add pp support * remove unused code * address conversation * fix memory leakage support tp+pp * move empty cache * move empty cache --------- Co-authored-by: Tong Li <tong.li35271158@gmail.com> --------- Co-authored-by: Tong Li <tong.li35271158@gmail.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: YeAnbang <anbangy2@outlook.com> Co-authored-by: duanjunwen <935724073@qq.com> Co-authored-by: YeAnbang <44796419+YeAnbang@users.noreply.github.com>
51 lines
1.5 KiB
Python
51 lines
1.5 KiB
Python
from ._operation import all_to_all_comm
|
|
from .attn import AttnMaskType, ColoAttention, RingAttention, get_pad_info
|
|
from .dropout import DropoutForParallelInput, DropoutForReplicatedInput
|
|
from .embedding import Embedding1D, PaddingEmbedding, VocabParallelEmbedding1D
|
|
from .linear import Linear1D_Col, Linear1D_Row, LinearWithGradAccum, PaddingLMHead, VocabParallelLMHead1D
|
|
from .loss import cross_entropy_1d, dist_cross_entropy, dist_log_prob, dist_log_prob_1d
|
|
from .normalization import FusedLayerNorm, FusedRMSNorm, LayerNorm, RMSNorm
|
|
from .parallel_module import ParallelModule
|
|
from .qkv_fused_linear import (
|
|
FusedLinear,
|
|
FusedLinear1D_Col,
|
|
FusedLinear1D_Row,
|
|
GPT2FusedLinearConv,
|
|
GPT2FusedLinearConv1D_Col,
|
|
GPT2FusedLinearConv1D_Row,
|
|
)
|
|
|
|
__all__ = [
|
|
"Embedding1D",
|
|
"VocabParallelEmbedding1D",
|
|
"LinearWithGradAccum",
|
|
"Linear1D_Col",
|
|
"Linear1D_Row",
|
|
"GPT2FusedLinearConv",
|
|
"GPT2FusedLinearConv1D_Row",
|
|
"GPT2FusedLinearConv1D_Col",
|
|
"DropoutForParallelInput",
|
|
"DropoutForReplicatedInput",
|
|
"cross_entropy_1d",
|
|
"dist_cross_entropy",
|
|
"dist_log_prob_1d",
|
|
"dist_log_prob",
|
|
"BaseLayerNorm",
|
|
"LayerNorm",
|
|
"RMSNorm",
|
|
"FusedLayerNorm",
|
|
"FusedRMSNorm",
|
|
"FusedLinear1D_Col",
|
|
"FusedLinear",
|
|
"ParallelModule",
|
|
"PaddingEmbedding",
|
|
"PaddingLMHead",
|
|
"VocabParallelLMHead1D",
|
|
"AttnMaskType",
|
|
"ColoAttention",
|
|
"RingAttention",
|
|
"get_pad_info",
|
|
"all_to_all_comm",
|
|
"FusedLinear1D_Row",
|
|
]
|