Skip to content

Issues: intel-analytics/ipex-llm

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
469 Open 8,445 Closed
469 Open 8,445 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[WIP] Refactor npu module
#12113 opened Sep 23, 2024 by lzivan Loading…
undefined symbol: iJIT_NotifyEvent with oneapi 2024.2, but no issue with 2024.0.1
#12112 opened Sep 23, 2024 by Jianshui
Running llama3.1 in ollama/langchain fails.
#12111 opened Sep 23, 2024 by tkarna
Add Qwen2.5 NPU Example
#12110 opened Sep 23, 2024 by JinBridger Loading…
[NPU] Qwen2 divide linear in decode layers
#12089 opened Sep 18, 2024 by cyita • Draft
1 of 9 tasks
[NPU] Add support for loading a FunASR model
#12073 opened Sep 13, 2024 by sgwhat Loading…
1 task
feat : add npu to ppl
#12071 opened Sep 12, 2024 by cranechu0131 Loading…
stablelm-zephyr-3b on NPU example
#12068 opened Sep 12, 2024 by jenniew Loading…
[WIP] support whisper on NPU
#12054 opened Sep 10, 2024 by plusbang • Draft
7 tasks
Update NPU Llama
#12031 opened Sep 6, 2024 by rnwang04 • Draft
1 task
[NPU] groupwise draft
#12022 opened Sep 5, 2024 by cyita • Draft
7 tasks
[WIP] Remove random in lookup update_candidate_strategy
#11986 opened Sep 2, 2024 by qiyuangong • Draft
7 tasks
On A770，vllm and llama.cpp which brings better performance for MiniCPM-v-2.6 ?
#11985 opened Sep 2, 2024 by yangqing-yq
@liu-shaojun
3
nightly test for 4.41.2
#11981 opened Aug 30, 2024 by songhappy Loading…
7 tasks
2
[WIP] fuse lm head on npu
#11980 opened Aug 30, 2024 by plusbang • Draft
2 tasks
2
how to use ipex-llm to run both the original and quantized versions of the Baichuan2 model on an Intel GPU
#11959 opened Aug 29, 2024 by tao-ov
1
Delete obsolete code for vLLM
#11821 opened Aug 16, 2024 by gc-fu Loading…
7 tasks
Qwen/Qwen2-7B-Instruct gives garbled outputs in LongBench with load_in_low_bit="fp16" and optimize_model=False
#11796 opened Aug 14, 2024 by ATMxsp01
Added yaml files for transformer 4.38.2 and updated performance test accordingly
#11730 opened Aug 7, 2024 by SichengStevenLi • Draft
Update Eagle example to Eagle2+ipex-llm integration
#11717 opened Aug 6, 2024 by jenniew Loading…
1
adapt npu
#11716 opened Aug 6, 2024 by yangw1234 Loading…
7 tasks
Update Arc nightly perf models
#11715 opened Aug 6, 2024 by SichengStevenLi Loading…
Impact with Intel Layoffs
#11710 opened Aug 2, 2024 by bratao
LLaVA example can not work when BIGDL_QUANTIZE_KV_CACHE=1
#11697 opened Jul 31, 2024 by ATMxsp01
Test For Transformers 4.41 Upgrade
#11684 opened Jul 30, 2024 by liu-shaojun • Draft
7 tasks
ProTip! no:milestone will show everything without a milestone.