Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / ollama/ollama issues and pull requests

#6734 - Error: pull model manifest: file does not exist (again)

Issue - State: closed - Opened by jamiejackherer 9 days ago - 2 comments
Labels: bug

#6733 - curl

Issue - State: closed - Opened by ayttop 9 days ago - 1 comment
Labels: bug

#6732 - add *_proxy to env map for debugging

Pull Request - State: closed - Opened by mxyng 9 days ago

#6731 - error wile install on opensuse leap 15.6

Issue - State: closed - Opened by kc8pdr205 9 days ago - 5 comments
Labels: bug

#6730 - api/embed return 404

Issue - State: closed - Opened by Maluuck 9 days ago - 2 comments
Labels: bug

#6729 - Feature: Add Support for Distributed Inferencing

Pull Request - State: open - Opened by ecyht2 9 days ago - 1 comment

#6728 - Add alias of /quit and /exit for /bye.

Issue - State: open - Opened by bulrush15 9 days ago
Labels: feature request

#6727 - Does ollama check for free disk space BEFORE pulling a new model?

Issue - State: closed - Opened by bulrush15 9 days ago - 1 comment
Labels: feature request

#6726 - "No Healthy Upstream" Error on Multiple Networks and Devices

Issue - State: closed - Opened by shake-hakobyan-rau 9 days ago - 1 comment
Labels: bug

#6725 - Incorrect AppDir when creating banner script (Preview)

Issue - State: open - Opened by DJStompZone 9 days ago
Labels: windows

#6724 - Tools Tag with "ollama show" command

Issue - State: closed - Opened by LilPiep 9 days ago - 2 comments
Labels: feature request

#6723 - How to change the system memory folder ?

Issue - State: closed - Opened by mdabir1203 9 days ago - 2 comments
Labels: bug

#6722 - MiniCPM3 support

Issue - State: open - Opened by IuvenisSapiens 9 days ago - 1 comment
Labels: model request

#6721 - Error loading model architecture for miniCPM3-4B: Unknown architecture 'minicpm3'

Issue - State: closed - Opened by ChuiyuWang1 9 days ago - 2 comments
Labels: model request

#6720 - Can you specify a graphics card in the ollama deployment model?

Issue - State: open - Opened by LIUKAI0815 9 days ago - 1 comment
Labels: feature request

#6719 - (111) Connection refused

Issue - State: closed - Opened by SheltonLiu-N 9 days ago - 4 comments
Labels: bug

#6718 - docs: update llama3 to llama3.1

Pull Request - State: closed - Opened by jmorganca 9 days ago

#6717 - Bubble up cuda library error codes with some retries

Pull Request - State: open - Opened by dhiltgen 9 days ago

#6716 - Quiet down dockers new lint warnings

Pull Request - State: closed - Opened by dhiltgen 9 days ago

#6715 - PC (GPU) crashing continusly with ollama and deepseek

Issue - State: open - Opened by pitziro 9 days ago - 2 comments
Labels: bug

#6714 - catch when model vocab size is set correctly

Pull Request - State: closed - Opened by pdevine 9 days ago

#6713 - Talking to Mistral-Nemo via OpenAI tool calling - fails

Issue - State: open - Opened by ChristianWeyer 10 days ago - 5 comments
Labels: bug

#6712 - 400 Bad Request when running behind Nginx Proxy Manager

Issue - State: open - Opened by Joly0 10 days ago - 12 comments
Labels: bug

#6710 - Docker: P8 State Power Usage double with 0.3.8+

Issue - State: closed - Opened by t3chn0m4g3 10 days ago - 7 comments
Labels: bug, nvidia

#6708 - Support tool/tool call ids when multiple tool calls are requested.

Issue - State: open - Opened by ggozad 10 days ago - 6 comments
Labels: bug

#6707 - Generate endpoint intermittently misses final token before done

Issue - State: closed - Opened by tarbard 10 days ago - 6 comments
Labels: bug, nvidia

#6706 - Reflection 70B has significant issue with the weights

Issue - State: closed - Opened by gileneusz 10 days ago - 4 comments
Labels: model request

#6704 - ollama model not support tool calling

Issue - State: open - Opened by sunshine19870316 10 days ago - 8 comments
Labels: feature request

#6703 - ollama and curl

Issue - State: closed - Opened by ayttop 11 days ago - 3 comments
Labels: bug, question

#6701 - Windows app gets confused if wsl2 based server is still running

Issue - State: closed - Opened by ares0027 11 days ago - 4 comments
Labels: feature request, windows, wsl

#6700 - MiniCPM3 not supported

Issue - State: closed - Opened by sataliulan 11 days ago - 3 comments
Labels: bug

#6697 - IGPUMemLimit/rocmMinimumMemory are undefined

Issue - State: closed - Opened by wangzd0209 11 days ago - 1 comment
Labels: question

#6694 - A mixture of experts model

Issue - State: closed - Opened by iplayfast 11 days ago - 1 comment
Labels: model request

#6692 - [Feature request] compatibility with vm balloon ram

Issue - State: open - Opened by Xyz00777 11 days ago - 2 comments
Labels: feature request

#6691 - Is everything fine with `phi3` model?

Issue - State: open - Opened by eirnym 12 days ago - 5 comments
Labels: bug

#6689 - Reflection 70B fix?

Issue - State: open - Opened by gileneusz 12 days ago - 2 comments
Labels: model request

#6686 - Model shows wrong date.

Issue - State: open - Opened by ghaisasadvait 12 days ago - 1 comment
Labels: bug

#6685 - AMD 7900XTX fails with `"Could not initialize Tensile host: No devices found"`

Issue - State: closed - Opened by svaningelgem 12 days ago - 48 comments
Labels: bug, docker

#6684 - Deepseek v2.5 sha256 digest mismatch

Issue - State: open - Opened by mintisan 12 days ago
Labels: bug

#6683 - docs: improve linux install documentation

Pull Request - State: closed - Opened by jmorganca 12 days ago

#6682 - Remove go server debug logging

Pull Request - State: closed - Opened by jessegross 12 days ago

#6681 - readme: add Plasmoid Ollama Control to community integrations

Pull Request - State: closed - Opened by imoize 13 days ago

#6680 - adding Archyve to community integrations list

Pull Request - State: closed - Opened by nickthecook 13 days ago

#6679 - HTTP_PROXY Not Being Used in Model Requests

Issue - State: open - Opened by cmilhaupt 13 days ago - 21 comments
Labels: bug

#6678 - OLLAMA_LOAD_TIMEOUT env variable not being applied

Issue - State: closed - Opened by YetheSamartaka 13 days ago - 7 comments
Labels: bug

#6677 - VG

Issue - State: closed - Opened by vioricavg 13 days ago - 2 comments

#6675 - Bugfix for #6656 (Fixed redirect check if direct URL is already Present)

Pull Request - State: open - Opened by Tobix99 13 days ago - 2 comments

#6674 - Simplify the input of multi-line text

Issue - State: open - Opened by linkoog 13 days ago - 1 comment
Labels: feature request

#6673 - Ollama-rocm on Kubernetes with shared AMD GPU seems to have problems allocating vram

Issue - State: closed - Opened by kubax 13 days ago - 4 comments
Labels: bug

#6672 - Inconsistent `prompt_eval_count` for Large Prompts in Ollama Python Library

Issue - State: closed - Opened by surajyadav91 13 days ago - 1 comment
Labels: bug

#6671 - Reflection 70B NEED Tools

Issue - State: closed - Opened by xiaoyu9982 13 days ago - 4 comments
Labels: model request

#6670 - expose slots data through API

Issue - State: closed - Opened by aiseei 13 days ago - 1 comment
Labels: feature request

#6669 - Ubuntu GPU not used

Issue - State: closed - Opened by Andrii-suncor 13 days ago - 1 comment
Labels: bug

#6668 - Every installed model disappeared

Issue - State: closed - Opened by yilmaz08 13 days ago - 6 comments
Labels: bug

#6667 - (Rebased) Add Braina AI as an Ollama Desktop GUI #2

Pull Request - State: open - Opened by wallacelance 13 days ago - 1 comment

#6666 - Improve logging on GPU too small

Pull Request - State: closed - Opened by dhiltgen 13 days ago

#6665 - Fix "presence_penalty_penalty" typo, add test.

Pull Request - State: closed - Opened by rick-github 13 days ago - 3 comments

#6664 - Reflection 70B model request

Issue - State: closed - Opened by gileneusz 13 days ago - 2 comments
Labels: model request

#6663 - Document uninstall on windows

Pull Request - State: closed - Opened by dhiltgen 13 days ago

#6658 - openai: support for structured outputs

Pull Request - State: open - Opened by iscy 14 days ago - 2 comments

#6654 - Multi-instance seems not working

Issue - State: closed - Opened by bigsausage 14 days ago - 4 comments
Labels: feature request

#6652 - Add Dracarys-Llama-3.1-70B-Instruct support

Issue - State: open - Opened by LSeu-Open 14 days ago - 2 comments
Labels: model request

#6649 - Intel GPU - model > 4b nonsense?

Issue - State: open - Opened by cyear 14 days ago - 5 comments
Labels: bug, intel

#6646 - POST /v1/chat/completions returns 404 not 400 for model not found

Issue - State: closed - Opened by codefromthecrypt 14 days ago - 3 comments
Labels: bug

#6645 - Fix gemma2 2b conversion

Pull Request - State: closed - Opened by pdevine 14 days ago

#6640 - OpenAI endpoint JSON output malformed

Issue - State: closed - Opened by defaultsecurity 15 days ago - 4 comments
Labels: bug

#6638 - Llama 3.1 8b not generating answers since past few days

Issue - State: open - Opened by ToshiKBhat 15 days ago - 8 comments
Labels: bug

#6631 - Add model Phi3-Vision

Issue - State: open - Opened by asmit203 15 days ago
Labels: model request

#6630 - docs(integrations): add claude-dev

Pull Request - State: open - Opened by sammcj 15 days ago

#6629 - Fail to Convert Huggingface Llama3.1 with ollama create

Issue - State: closed - Opened by YueChenkkk 15 days ago - 4 comments
Labels: bug

#6628 - no space left on device - ubuntu

Issue - State: open - Opened by fahadshery 15 days ago
Labels: bug

#6627 - Add preliminary support for riscv64

Pull Request - State: open - Opened by mengzhuo 15 days ago - 2 comments

#6626 - unable to load cuda driver library . symbol lookup for cuCtxCreate_v3 failed

Issue - State: closed - Opened by Wangzg97 15 days ago - 1 comment
Labels: bug

#6625 - Support for HuatuoGPT-Vision-7B

Issue - State: open - Opened by Chuyun-Shen 15 days ago
Labels: model request

#6624 - Update README.md with PyOllaMx

Pull Request - State: closed - Opened by kspviswa 15 days ago - 1 comment

#6623 - nvidia/NV-Embed-v2 support

Issue - State: open - Opened by youxiaoxing 15 days ago - 4 comments
Labels: model request

#6622 - [Bug] open-webui integration error when ui docker listen on 11434

Issue - State: open - Opened by zydmtaichi 15 days ago - 1 comment
Labels: bug

#6621 - llama: sync llama.cpp to commit 8962422

Pull Request - State: open - Opened by jmorganca 15 days ago

#6620 - Use cuda v11 for driver 525 and older

Pull Request - State: closed - Opened by dhiltgen 15 days ago

#6619 - Go Server Health Reporting

Pull Request - State: closed - Opened by jessegross 15 days ago

#6618 - llm: update llama.cpp commit to 8962422

Pull Request - State: closed - Opened by jmorganca 15 days ago - 1 comment

#6617 - Log system memory at info

Pull Request - State: closed - Opened by dhiltgen 15 days ago

#6616 - A100 shared GPU - Server not responding (always after some time where it works)

Issue - State: closed - Opened by Ida-Ida 15 days ago - 12 comments
Labels: bug, performance, nvidia

#6615 - api: add Client.BaseURL method

Pull Request - State: open - Opened by presbrey 15 days ago

#6614 - Update README.md

Pull Request - State: open - Opened by cfjedimaster 16 days ago

#6607 - docker image for rocm-3.5.1 to run on older AMD gpus

Issue - State: closed - Opened by drhboss 16 days ago - 1 comment
Labels: feature request

#6604 - `your nvidia driver is too old or missing` error

Issue - State: open - Opened by my106 16 days ago - 1 comment
Labels: nvidia, needs more info

#6601 - when i try to visit https://xxxxxxxx.com/api/chat，it is very slow

Issue - State: closed - Opened by lessuit 16 days ago - 3 comments
Labels: needs more info

#6596 - Unloading a model

Issue - State: closed - Opened by tallesl 17 days ago - 4 comments
Labels: feature request

#6595 - 4 AMD GPUs with mixed VRAM sizes: layer predictions incorrect leads to runner crash

Issue - State: open - Opened by MikeLP 17 days ago - 13 comments
Labels: bug, amd, memory

#6593 - Get supported models with API

Issue - State: open - Opened by angelozerr 17 days ago
Labels: feature request

#6592 - Model whitelisting for generate endpoint

Issue - State: open - Opened by JTHesse 17 days ago
Labels: feature request

#6591 - Ollama failing with `CUDA error: PTX JIT compiler library not found`

Issue - State: closed - Opened by leobenkel 17 days ago - 2 comments
Labels: bug