Skip to content

Pull requests: PaddlePaddle/PaddleNLP

New pull request New
278 Open 4,922 Closed
278 Open 4,922 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

support Llama3.1 8B 128K generation on single GPU 80GB
#8811 opened Jul 25, 2024 by GuoxiaWang Loading…
1
[MoE] Optimizer parameter broadcast
#8810 opened Jul 25, 2024 by DesmonDay Loading…
7
add fp8 cutlass gemm fused op for llama2 inference
#8809 opened Jul 25, 2024 by Sunny-bot1 Loading…
2
suppoet qwen2 inferece model
#8806 opened Jul 25, 2024 by Sunny-bot1 Loading…
1
[LLM] 动态图推理
#8804 opened Jul 25, 2024 by zhoutianzi666 Loading…
1
[Unified Checkpoint] update async save
#8801 opened Jul 24, 2024 by DesmonDay Loading…
2
add tune_gemm feature contributor
#8799 opened Jul 24, 2024 by Hanyonggong Loading…
@KB-Ding
15
longlora implement contributor
#8798 opened Jul 24, 2024 by micelvrice Loading…
@KB-Ding
5
[Unified Checkpoint] Fix tie_word_embeddings
#8795 opened Jul 23, 2024 by DesmonDay Loading…
2
[CI] Fix
#8793 opened Jul 23, 2024 by DrownFish19 Loading…
2
Revised Pose contributor
#8788 opened Jul 19, 2024 by whf313 Loading…
@ZHUI
3
[LLM]Update yuan model contributor
#8786 opened Jul 19, 2024 by zhaogf01 Loading…
@ZHUI
18
add paddle nv-embed-v1 contributor
#8785 opened Jul 19, 2024 by Li-Z-Q Loading…
@ZHUI
8
[AutoParallel] Refine save load contributor
#8783 opened Jul 19, 2024 by xingmingyyj Loading…
@ZHUI
7
[Model] Add resized_lm_head
#8770 opened Jul 16, 2024 by DrownFish19 Loading…
3
[AutoParallel] Refine auto_trainer save load
#8767 opened Jul 16, 2024 by zhangbo9674 Loading…
9
Hetertrain
#8763 opened Jul 15, 2024 by Difers Loading…
2
support Llama2 fp8c16 inference
#8762 opened Jul 14, 2024 by Sunny-bot1 Loading…
2
[Fix] Enable tensor parallel tests.
#8757 opened Jul 12, 2024 by ZHUI Loading…
2
fix the tipc ce case
#8748 opened Jul 10, 2024 by wawltor Loading…
2
Do Not Merge, [XPU], use paddle's fused_rms_norm instead of paddle_xpu_nn's in llama
#8746 opened Jul 10, 2024 by cqulilujia Loading…
2
[Tokenizer] TokenizerFast
#8735 opened Jul 9, 2024 by DrownFish19 • Draft
2
add param translator
#8729 opened Jul 8, 2024 by zhangbo9674 Loading…
1
Hybrid quantization algorithm based on lqlora contributor
#8724 opened Jul 7, 2024 by Liebele Loading…
@wj-Mcat
8
Add reft method contributor
#8723 opened Jul 7, 2024 by TranscenderNing Loading…
@wj-Mcat
12
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.