Skip to content

Issues: ollama/ollama

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

714 Open 2,092 Closed
714 Open 2,092 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

It is possible to enable OpenAI Api in Docker image feature request New feature or request
#4475 opened May 16, 2024 by Tomichi
support image with url when chat with vison model feature request New feature or request
#4474 opened May 16, 2024 by dickens88
InternVL model request Model requests
#4473 opened May 16, 2024 by enryteam
llama3-chatqa always returns Empty reponse bug Something isn't working
#4472 opened May 16, 2024 by pnmartinez
Warning: client version is different than Ollama version in Linux bug Something isn't working
#4471 opened May 16, 2024 by sohang3112
"ollama list" should display creation time, not download time feature request New feature or request
#4470 opened May 16, 2024 by LaurentBonnaud
Ollama memory consumption bug Something isn't working
#4469 opened May 16, 2024 by hugefrog
Ollama speed dropped with setting OLLAMA_NUM_PARALLEL bug Something isn't working
#4468 opened May 16, 2024 by hugefrog
Add new model error feature request New feature or request
#4466 opened May 16, 2024 by momo8zero
Zluda not working with Ollama's version(0.1.33 to 0.1.38) using RX6600 on windows 10 bug Something isn't working
#4464 opened May 16, 2024 by usmandilmeer
2
Error: llama runner process has terminated: exit status 0xc0000409 bug Something isn't working
#4457 opened May 15, 2024 by xdfnet
1
[REPORTING] For arch or arch based linux users storage path for models is /var/lib/ollama/.ollama/models/blobs
#4455 opened May 15, 2024 by HakaishinShwet
Ollama + sentence-transformers with torch cuda bug Something isn't working
#4453 opened May 15, 2024 by qsdhj
openai.error.InvalidRequestError: model 'deepseek-coder:6.7b' not found, try pulling it first bug Something isn't working
#4449 opened May 15, 2024 by userandpass
Streaming Chat Completion via OpenAI API should support stream option to include Usage feature request New feature or request
#4448 opened May 15, 2024 by odrobnik
JSON Mode + Streaming + OpenAI API + Llama3 = never sends STOP, and a lot of whitespace after the JSON bug Something isn't working
#4446 opened May 15, 2024 by odrobnik
1
Add tab completions for fish shell feature request New feature or request
#4444 opened May 15, 2024 by coder543
Models remain resident in VRAM after deletion bug Something isn't working
#4443 opened May 15, 2024 by coder543
Error: llama runner process has terminated: exit status 0xc0000409 bug Something isn't working
#4442 opened May 15, 2024 by hcr707305003
3
Add support for third-party hosted APIs feature request New feature or request
#4440 opened May 14, 2024 by 19h
1
Ollama vs Llama-cpp-python : Slow response time as compared to llama-cpp-python bug Something isn't working gpu nvidia Issues relating to Nvidia GPUs and CUDA
#4437 opened May 14, 2024 by utility-aagrawal
2
GPU layer control / prioritisation feature request New feature or request
#4433 opened May 14, 2024 by AncientMystic
Lora models / Lora training feature request New feature or request
#4432 opened May 14, 2024 by AncientMystic
1
BUG: Custom System Prompt not loading bug Something isn't working
#4431 opened May 14, 2024 by MichaelFomenko
ollama can't run qwen:72b, error msg ""gpu VRAM usage didn't recover within timeout bug Something isn't working
#4427 opened May 14, 2024 by changingshow
ProTip! Adding no:label will show everything without a label.