Skip to content

Pull requests: PaddlePaddle/PaddleNLP

New pull request New
295 Open 5,257 Closed
295 Open 5,257 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

[Unified Checkpoint] Fix generation config save
#9223 opened Sep 30, 2024 by DrownFish19 Loading…
2
[INFER] update tune_cublaslt_gemm op and fix some bugs
#9222 opened Sep 30, 2024 by yuanlehome Loading…
2
[Readme] Add flash mask
#9219 opened Sep 30, 2024 by lugimzzz Loading…
5
[Auto Parallel] fix bugs for split_batches_for_accumulation && fix bu…
#9217 opened Sep 29, 2024 by zhangyuqin1998 Loading…
3
[Tokenizer] Support reading Tiktoken tokenizer.model.
#9215 opened Sep 28, 2024 by lvdongyi Loading…
2
[NPU] Add chatglmv3-6b 多硬件
#9213 opened Sep 27, 2024 by Jakin-huang Loading…
3
[llm]support long sequence training
#9208 opened Sep 26, 2024 by lugimzzz Loading…
8
[LLM] update tensor and pipeline parallel for chatglmv2
#9204 opened Sep 26, 2024 by DrownFish19 Loading…
1
[AutoParallel] Add test for fuse_ffn and fuse_attention_qkv pass
#9203 opened Sep 26, 2024 by zhangbo9674 Loading…
1
[LLM INFER] top_p_sampling_reject support top_p=0 and custom seed
#9202 opened Sep 26, 2024 by gzy19990617 Loading…
1
【Inference】Optimize fuse some kernels
#9201 opened Sep 26, 2024 by gzy19990617 Loading…
1
[intel_hpu] initial commit for intel_hpu support
#9195 opened Sep 25, 2024 by yanfeich Loading…
3
[DON'T NEED REVIEW] Mthreads llama 13 b 多硬件
#9193 opened Sep 25, 2024 by shang-mt Loading…
1
[METAX] Support llama for MX C550 多硬件
#9186 opened Sep 24, 2024 by idontkonwher Loading…
1
[Unified Checkpoint] Checkpoint compression init
#9183 opened Sep 23, 2024 by wtmlon Loading…
3
[WIP] Support speculative decoding inference
#9180 opened Sep 23, 2024 by Wanglongzhi2001 Loading…
1
Ckpt quant
#9178 opened Sep 23, 2024 by wtmlon Loading…
1
[Auto Parallel] add align mode supporting
#9165 opened Sep 21, 2024 by zhangyuqin1998 Loading…
1
[Typos] Fix typos of code base.
#9164 opened Sep 21, 2024 by co63oc Loading…
3
[XPU] rename SP Layer name to enable checkpoint loading from GPU
#9163 opened Sep 21, 2024 by lj970926 Loading…
1
[Auto Parallel] Adding align mode support
#9150 opened Sep 18, 2024 by zhangyuqin1998 Loading…
3
Add timer for Paddle optimizer (#7563) (#9128)
#9147 opened Sep 18, 2024 by ForFishes Loading…
3
[LLM] add token metrics after regular & save step
#9146 opened Sep 14, 2024 by SylarTiaNII Loading…
3
add config file for model chatglm2,gemma,yuan
#9139 opened Sep 13, 2024 by Mangodadada Loading…
25
[LLM] Add tools for parameters
#9137 opened Sep 13, 2024 by Hanyonggong Loading…
13
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.