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

734 Open 1,863 Closed
734 Open 1,863 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

OLLAMA_NUM_PARALLEL and multi-modal models lead to failed processing images error bug Something isn't working
#4165 opened May 5, 2024 by jmorganca
llava broke in new version v0.1.33 bug Something isn't working
#4163 opened May 5, 2024 by VideoFX
1
@jmorganca
4
implement LRU cache for GPU VRAM when inferencing MoE model feature request New feature or request
#4161 opened May 5, 2024 by davinwang
On Windows , with version 0.1.33 assembling two models creates a path error. Version 0.1.32 works correctly. bug Something isn't working
#4158 opened May 5, 2024 by amonpaike
@mxyng
Bunny-Llama-3-8B-V model request Model requests
#4157 opened May 5, 2024 by rawzone
1
Can't delete all characters when typing in non-english characters. bug Something isn't working
#4156 opened May 4, 2024 by ktkalpha
1
Add option in the install scripts to auto set OLLAMA_HOST environment variable feature request New feature or request
#4155 opened May 4, 2024 by centopw
v0.1.33 can't load gemma:7b-instruct-v1.1-fp16 due to failed to create context with model bug Something isn't working
#4152 opened May 4, 2024 by MarkWard0110
1
mixtral:8x22b causes intermittent system freezes on Mac, runs very slow bug Something isn't working
#4151 opened May 4, 2024 by joliss
Supports the computing power of NPUs and GPUs provided by Intel Ultra processors feature request New feature or request
#4150 opened May 4, 2024 by Perry961002
Importing a Mistral finetune into Ollama fails with invalid file magic bug Something isn't working
#4148 opened May 4, 2024 by BruceMacD
More Quants for command-r-plus Please? model request Model requests
#4142 opened May 3, 2024 by chigkim
1
Original 2gb and 4gb Jetson Nano Developer Kits (Not Orin Version) - GPU Possible? feature request New feature or request nvidia Issues relating to Nvidia GPUs and CUDA
#4140 opened May 3, 2024 by dtischler
only 1 GPU found -- regression 1.32 -> 1.33 bug Something isn't working nvidia Issues relating to Nvidia GPUs and CUDA
#4139 opened May 3, 2024 by AlexLJordan
@dhiltgen
8
Support for HyperGAI/HPT1_5-Air-Llama-3-8B-Instruct-multimodal model request Model requests
#4137 opened May 3, 2024 by Extremys
[Feature] Rapid Modelfile Updates feature request New feature or request
#4136 opened May 3, 2024 by Arcitec
1
WithSecure quarantined ollama_llama_server.exe as harmful file / Malware bug Something isn't working windows
#4134 opened May 3, 2024 by sjdevcode
@dhiltgen
2
"which/max" command line options to help with sizing. feature request New feature or request
#4133 opened May 3, 2024 by bigattichouse
model run command not rendered on mobile feature request New feature or request ollama.com
#4132 opened May 3, 2024 by userforsource
@BruceMacD
5
Error "timed out waiting for llama runner to start: " on larger models. bug Something isn't working
#4131 opened May 3, 2024 by CalvesGEH
1
Docker Build is failing because libcurl-httpd24 .so.4 cannot be loaded bug Something isn't working docker Issues relating to using ollama in containers
#4130 opened May 3, 2024 by SoniCoder
@dhiltgen
1
Normalization of output from embedding model feature request New feature or request
#4128 opened May 3, 2024 by hagemon
Add LLAVA++ model model request Model requests
#4127 opened May 3, 2024 by ddpasa
Some Ollama models apparently affected by llama.cpp BPE pretokenization issue bug Something isn't working
#4126 opened May 3, 2024 by sealad886
/api/embeddings responds with 500 before Ollama is initialized - handle max queued requests failure better bug Something isn't working windows
#4124 opened May 3, 2024 by maxggl
1
@dhiltgen
5
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.