Skip to content

Pull requests: PaddlePaddle/PaddleNLP

New pull request New
393 Open 6,443 Closed
393 Open 6,443 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Wintx unzip
#10674 opened May 29, 2025 by ZhangX-21 Loading…
2 tasks
1
[Auto-Parallel] Add benchmark for sharding opt in qwen N4C32 dy_auto
#10673 opened May 29, 2025 by Xing-lil Loading…
2 tasks
1
Patch zip overflow
#10672 opened May 29, 2025 by A-nnonymous Loading…
1
[Auto-Parallel] optimize llama-7b benchmark in temporary solution to …
#10671 opened May 29, 2025 by liym27 Loading…
2 tasks
1
[tests] migrate to unittest.assertEqual contributor HappyOpenSource 快乐开源活动issue与PR
#10670 opened May 28, 2025 by emmanuel-ferdman Loading…
1 of 2 tasks
@luotao1 @ZHUI
1
refine fp8 code
#10669 opened May 28, 2025 by zhangbo9674 Loading…
2 tasks
1
add mistral for paddlenlp/experimental/transformers contributor
#10668 opened May 28, 2025 by Li-Z-Q Loading…
@KB-Ding
1
Support fastsafetensors to load model contributor
#10667 opened May 28, 2025 by zeroRains Loading…
1 of 2 tasks
@yuanlehome @KB-Ding
1
[AutoParallel] improve qwen rms norm custom op performance
#10659 opened May 27, 2025 by waliwali777 Loading…
2 tasks
1
[CI] Update test_modeling.py
#10658 opened May 27, 2025 by HydrogenSulfate Loading…
2 tasks
1
Add fused_transpose_split_quant kernel
#10657 opened May 26, 2025 by lshpku Loading…
1
Add llama-13b dynamic auto benchmark
#10654 opened May 26, 2025 by waliwali777 Loading…
2 tasks
1
Update model_utils.py
#10650 opened May 24, 2025 by wangguan1995 Loading…
2
llama_with_auto_pp
#10648 opened May 23, 2025 by Waynezee Loading…
2 tasks
2
【Inference Optimize】update moe config
#10646 opened May 23, 2025 by chang-wenbin Loading…
2 tasks
1
Add fused_transpose_quant op
#10644 opened May 23, 2025 by lshpku Loading…
1
[workflow] Add workflow yaml contributor
#10643 opened May 23, 2025 by Liujie0926 Loading…
2 tasks
@wawltor
2
[CI] skip unit case for hang contributor
#10642 opened May 23, 2025 by Liujie0926 Loading…
2 tasks
@wawltor
2
Apply merge and split function for mp_reshard contributor
#10637 opened May 22, 2025 by fjjF77 Loading…
@KB-Ding
2
LLaMa vpp 组网
#10634 opened May 22, 2025 by Waynezee Loading…
2 tasks
2
[Template] add unified template.
#10633 opened May 22, 2025 by wtmlon Loading…
3
Remove baichuan13b hidden layers in dynamic auto mode
#10624 opened May 21, 2025 by Function-Samuel Loading…
2 tasks
2
run llama13b custom op perf
#10622 opened May 20, 2025 by waliwali777 Loading…
2 tasks
1
[llm] support tensorwise fp8/int8 training
#10612 opened May 19, 2025 by lugimzzz Loading…
18
Test the improve in hand_dy llama7b tensor_fusion and sharding overlap
#10602 opened May 16, 2025 by Xing-lil Loading…
2 tasks
1
ProTip! What’s not been updated in a month: updated:<2025-04-28.