ollama/ollama issues and pull requests

#6382 - cuda error out of memory

Issue - State: open - Opened by qazimurtazafair about 1 month ago - 12 comments
Labels: bug, nvidia, memory

#6382 - cuda error out of memory

Issue - State: open - Opened by qazimurtazafair about 1 month ago - 11 comments
Labels: bug

#6381 - fix: Add tooltip to system tray icon

Pull Request - State: closed - Opened by eust-w about 1 month ago - 1 comment

#6381 - fix: Add tooltip to system tray icon

Pull Request - State: closed - Opened by eust-w about 1 month ago - 1 comment

#6380 - Hangs after 20-30 mins, a perdiocal restart of the ollama service is required

Issue - State: open - Opened by itinance about 1 month ago - 2 comments
Labels: bug

#6380 - Hangs after 20-30 mins, a perdiocal restart of the ollama service is required

Issue - State: open - Opened by itinance about 1 month ago - 6 comments
Labels: bug

#6379 - Separate ARM64 CPU builds from x64 CPU builds and use Clang instead

Pull Request - State: closed - Opened by hmartinez82 about 1 month ago - 1 comment

#6379 - Separate ARM64 CPU builds from x64 CPU builds and use Clang instead

Pull Request - State: open - Opened by hmartinez82 about 1 month ago

#6378 - Add confichat to README.md

Pull Request - State: open - Opened by 1runeberg about 1 month ago

#6378 - Add confichat to README.md

Pull Request - State: open - Opened by 1runeberg about 1 month ago

#6377 - Full(er) JSON Schema support for tool calling

Issue - State: open - Opened by mitar about 1 month ago - 2 comments
Labels: feature request

#6376 - Dynamic Functions Load

Issue - State: open - Opened by ivostoykov about 1 month ago
Labels: feature request

#6376 - Dynamic Functions Load

Issue - State: open - Opened by ivostoykov about 1 month ago
Labels: feature request

#6375 - Update Dockerfile

Pull Request - State: closed - Opened by kallados about 1 month ago - 2 comments

#6375 - Update Dockerfile

Pull Request - State: closed - Opened by kallados about 1 month ago - 2 comments

#6374 - feat: support for markdown rendering in the cli - wip

Pull Request - State: open - Opened by ukd1 about 1 month ago - 1 comment

#6374 - feat: support for markdown rendering in the cli - wip

Pull Request - State: open - Opened by ukd1 about 1 month ago

#6373 - The layer of model created by Modelfile has 600 permission

Issue - State: closed - Opened by zwwhdls about 1 month ago - 6 comments
Labels: bug

#6373 - The layer of model created by Modelfile has 600 permission

Issue - State: open - Opened by zwwhdls about 1 month ago - 6 comments
Labels: bug

#6372 - System tray icon is empty

Issue - State: closed - Opened by Biyakuga about 1 month ago - 1 comment
Labels: bug, windows

#6372 - System tray icon is empty

Issue - State: closed - Opened by Biyakuga about 1 month ago - 1 comment
Labels: bug, windows

#6371 - Modelfile created by importing a GGUF does not seem to do template detection

Issue - State: closed - Opened by jparismorgan about 1 month ago - 8 comments
Labels: bug

#6370 - Error: llama runner process no longer running: -1

Issue - State: closed - Opened by josephyuzb about 1 month ago - 3 comments
Labels: bug, needs more info

#6369 - Ubuntu22.04 - Warning: could not connect to a running Ollama instance

Issue - State: closed - Opened by ACodingfreak about 1 month ago - 3 comments
Labels: bug

#6369 - Ubuntu22.04 - Warning: could not connect to a running Ollama instance

Issue - State: closed - Opened by ACodingfreak about 1 month ago - 3 comments
Labels: bug

#6368 - Please add socks5 proxy func to download models ！Because the internet in China is not accessible

Issue - State: closed - Opened by icetech233 about 1 month ago - 2 comments
Labels: feature request

#6368 - Please add socks5 proxy func to download models ！Because the internet in China is not accessible

Issue - State: closed - Opened by icetech233 about 1 month ago - 1 comment
Labels: feature request

#6367 - Please add support for Audio models such as Qwen2-Audio

Issue - State: closed - Opened by carlosforster about 1 month ago - 2 comments
Labels: feature request

#6366 - Unable to Pull Model Manifest - "Get https://registry.ollama.ai/v2/library/llama3/manifests/latest: EOF"

Issue - State: closed - Opened by uestcxt about 1 month ago - 4 comments
Labels: bug, needs more info

#6366 - Unable to Pull Model Manifest - "Get https://registry.ollama.ai/v2/library/llama3/manifests/latest: EOF"

Issue - State: open - Opened by uestcxt about 1 month ago - 1 comment
Labels: bug

#6365 - Moondream fails at some images, unexpected output/messages?

Issue - State: closed - Opened by carlosforster about 1 month ago - 12 comments
Labels: bug

#6364 - docker container can't detect Nvidia GPU

Issue - State: open - Opened by fahadshery about 1 month ago - 26 comments
Labels: bug, nvidia, docker

#6363 - fix: noprune on pull

Pull Request - State: closed - Opened by mxyng about 1 month ago

#6363 - fix: noprune on pull

Pull Request - State: closed - Opened by mxyng about 1 month ago

#6358 - Segmentation fault

Issue - State: closed - Opened by yicheng-2019 about 1 month ago - 4 comments
Labels: bug, needs more info

#6358 - Segmentation fault

Issue - State: open - Opened by yicheng-2019 about 1 month ago - 3 comments
Labels: bug

#6357 - Error: unknown data type: U8

Issue - State: closed - Opened by YaBoyBigPat about 1 month ago - 26 comments

#6357 - Error: unknown data type: U8

Issue - State: open - Opened by YaBoyBigPat about 1 month ago - 9 comments

#6356 - AMD Multiple GPU support

Issue - State: open - Opened by VitalickS about 1 month ago - 2 comments
Labels: bug, windows, amd

#6354 - Embedding interface routing

Issue - State: closed - Opened by xuzeyu91 about 1 month ago - 2 comments
Labels: feature request

#6354 - Embedding interface routing

Issue - State: closed - Opened by xuzeyu91 about 1 month ago - 3 comments
Labels: feature request

#6353 - Very slow API generate endpoint

Issue - State: closed - Opened by mann1x about 1 month ago - 9 comments
Labels: bug, nvidia, needs more info

#6352 - The quality of answer significantly deteriorates after Automatic Quantization

Issue - State: open - Opened by garyyang85 about 1 month ago
Labels: bug

#6351 - ollama tool input: string with newline character (\n) is cutoff

Issue - State: open - Opened by remon-rakibul about 1 month ago - 2 comments
Labels: bug

#6350 - Is this wrong in https://ollama.com/blog/gemma2

Issue - State: closed - Opened by wonpn about 1 month ago - 2 comments
Labels: bug

#6350 - Is this wrong in https://ollama.com/blog/gemma2

Issue - State: closed - Opened by wonpn about 1 month ago - 2 comments
Labels: bug

#6349 - add `CONTRIBUTING.md`

Pull Request - State: closed - Opened by jmorganca about 1 month ago

#6349 - add `CONTRIBUTING.md`

Pull Request - State: closed - Opened by jmorganca about 1 month ago

#6348 - Mistral 7B, running on CPU only - can't fix it

Issue - State: closed - Opened by openSourcerer9000 about 1 month ago - 2 comments
Labels: bug

#6348 - Mistral 7B, running on CPU only - can't fix it

Issue - State: closed - Opened by openSourcerer9000 about 1 month ago - 2 comments
Labels: bug

#6347 - server: reduce max connections used in download

Pull Request - State: closed - Opened by bmizerany about 1 month ago - 5 comments

#6346 - lint

Pull Request - State: closed - Opened by mxyng about 1 month ago

#6346 - lint

Pull Request - State: closed - Opened by mxyng about 1 month ago

#6345 - Update openai.md to remove extra checkbox for vision

Pull Request - State: closed - Opened by pamelafox about 1 month ago

#6344 - update chatml template format to latest

Pull Request - State: closed - Opened by BruceMacD about 1 month ago

#6344 - update chatml template format to latest

Pull Request - State: closed - Opened by BruceMacD about 1 month ago

#6343 - Go back to a pinned Go version

Pull Request - State: closed - Opened by dhiltgen about 1 month ago

#6342 - Windows Defender

Issue - State: closed - Opened by Eniti-Codes about 1 month ago - 1 comment
Labels: bug

#6342 - Windows Defender

Issue - State: closed - Opened by Eniti-Codes about 1 month ago - 1 comment
Labels: bug

#6341 - Llama 3.1 70B high-quality HQQ quantized model - 99%+ quality of fp16

Issue - State: open - Opened by gileneusz about 1 month ago - 1 comment
Labels: model request

#6341 - Llama 3.1 70B high-quality HQQ quantized model - 99%+ quality of fp16

Issue - State: open - Opened by gileneusz about 1 month ago - 2 comments
Labels: model request

#6340 - Add new chat app LLMChat.co

Pull Request - State: open - Opened by deep93333 about 1 month ago - 3 comments

#6340 - Add new chat app LLMChat.co

Pull Request - State: open - Opened by deep93333 about 1 month ago

#6339 - ollama - default tool support

Issue - State: open - Opened by Kreijstal about 1 month ago
Labels: feature request

#6339 - ollama - default tool support

Issue - State: open - Opened by Kreijstal about 1 month ago
Labels: feature request

#6338 - ollama slower than llama.cpp

Issue - State: open - Opened by phly95 about 1 month ago - 8 comments
Labels: bug, performance, windows, nvidia

#6338 - ollama slower than llama.cpp

Issue - State: open - Opened by phly95 about 1 month ago - 9 comments
Labels: bug, performance, windows, nvidia

#6337 - Why is the occupancy of my Llama 3 model not high when using the GPU NV T2000, but instead it is computing using the CPU?

Issue - State: open - Opened by pewjs about 1 month ago - 6 comments
Labels: bug

GitHub / ollama/ollama issues and pull requests