Pull requests: huggingface/optimum-intel

22 Open 661 Closed

Author

Filter by author

author:

Filter by this user

Label

Filter by label

Projects

Filter by project

Milestones

Filter by milestone

Reviews

Filter by reviews

No reviews Review required Approved review Changes requested

Assignee

Filter by who’s assigned

Assigned to nobody

assignee:

Filter by this user

Sort

Sort by

Newest Oldest Most commented Least commented Recently updated Least recently updated Best match

Most reactions

👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

loading generation config if it is part of model

#750 opened Jun 6, 2024 by eaidova Loading…

1 of 3 tasks

2

Fix TemporaryDirectory error when exporting models on Windows

#749 opened Jun 5, 2024 by helena-intel Loading…

4

multi instances of infer

#744 opened Jun 4, 2024 by wgzintel • Draft

2

Add OpenVINO pipelines

#740 opened May 31, 2024 by echarlaix Loading…

1

Temporary PR to check CI status for new openvino release

#734 opened May 29, 2024 by nikita-savelyevv • Draft

1

[WIP] Enable IPEXModel with deepspeed

#732 opened May 28, 2024 by jiqing-feng Loading…

1

refactor CPU llama inference code

#728 opened May 26, 2024 by faaany Loading…

19

fix olmo accuracy for bf16, add sdpa for persimmon, support jais

#726 opened May 23, 2024 by eaidova Loading…

7

ipex 2.3 released

#725 opened May 23, 2024 by jiqing-feng Loading…

30

dump model before compress cli

#723 opened May 22, 2024 by eaidova • Draft

3 tasks

7

optionally enable export if not exported model provided

#722 opened May 21, 2024 by eaidova Loading…

3 tasks

5

[OV] Move data-driven quantization after model export for text-generation models

#721 opened May 21, 2024 by nikita-savelyevv Loading…

1 of 3 tasks

24

add IPEX-XPU support for Llama2 model Inference

#703 opened May 8, 2024 by faaany • Draft

5

[OV] Sets symbols on inputs and variables

#696 opened May 1, 2024 by jane-intel • Draft

Add test for INC examples

#617 opened Mar 19, 2024 by echarlaix • Draft

1

proper filter for applying bettertransformer

#610 opened Mar 17, 2024 by eaidova • Draft

3 tasks

2

concurrency without model cloning

#573 opened Feb 27, 2024 by dtrawins Loading…

1 of 2 tasks

39

Concurrency support using model clone

#564 opened Feb 16, 2024 by dtrawins Loading…

2 tasks done

5

Create infer request per inference to enable concurrency

#494 opened Dec 21, 2023 by mzegla • Draft

3

Added hybrid quantization for seq2seq models

#427 opened Sep 8, 2023 by AlexKoff88 Loading…

3

Export the decoder only once for seq2seq models

#307 opened May 2, 2023 by echarlaix • Draft

1

Add JPQD evaluation notebook

#231 opened Mar 12, 2023 by helena-intel • Draft

3