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

Clear current search query, filters, and sorts
428 Open 636 Closed
428 Open 636 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

[Feature] Support Intel GPUs feature request New feature or request
#8414 opened Jan 14, 2025 by NeoZhangJianyu
3
Running the same model on all GPUs feature request New feature or request gpu
#8404 opened Jan 13, 2025 by ZanMax
1
Allow building with BLAS/BLIS now that Ollama's runners are not pure native builds of llama.cpp anymore feature request New feature or request
#8402 opened Jan 13, 2025 by hmartinez82
Return in a response a flag if the input request was truncated feature request New feature or request
#8386 opened Jan 11, 2025 by MarkWard0110
1
Support Code Actions feature request New feature or request
#8368 opened Jan 9, 2025 by asmith26
2
When I use multiple GPUs, the utilization is very low.How can I configure it to maximize GPU utilization and reduce the reasoning time? feature request New feature or request
#8365 opened Jan 9, 2025 by RoRui
4
we need Ollama Video-LLaVA feature request New feature or request
#8355 opened Jan 9, 2025 by ixn3rd3mxn
Dynamic context size in OpenAI API compatibility. feature request New feature or request
#8354 opened Jan 9, 2025 by x0wllaar
1
[feature] start ollama automatically on startup feature request New feature or request
#8341 opened Jan 7, 2025 by remco-pc
Make flash attention configurable via UI or enable by default feature request New feature or request
#8335 opened Jan 7, 2025 by HDembinski
Allow set the type of K/V cache separately feature request New feature or request
#8332 opened Jan 7, 2025 by ag2s20150909
Add a CUDA+AVX2(VNNI) runner to the Docker image. feature request New feature or request
#8324 opened Jan 6, 2025 by x0wllaar
Feature Request: Limit Ollama to use only GPU RAM (VRAM), not system RAM feature request New feature or request
#8316 opened Jan 6, 2025 by mlibre
4
Improve speed on cpu-only feature request New feature or request
#8306 opened Jan 4, 2025 by ErfolgreichCharismatisch
1
Ollama - Gentoo Linux support feature request New feature or request
#8293 opened Jan 3, 2025 by jaypeche
3
disable cpu offload for runing llm feature request New feature or request
#8291 opened Jan 3, 2025 by verigle
3
Enable auto-save functionality via CLI flag feature request New feature or request
#8288 opened Jan 2, 2025 by migueltorrescosta
@pdevine
1
Allow use of locally installed CUDA or ROCm feature request New feature or request
#8286 opened Jan 2, 2025 by erkinalp
1
Community Contribution: Open-Source Chinese Tutorial for Ollama feature request New feature or request
#8269 opened Dec 30, 2024 by AXYZdong
Option to show all models available from registry/library feature request New feature or request
#8241 opened Dec 25, 2024 by t18n
@bmizerany
2
version aware linux upgrade feature request New feature or request install linux
#8233 opened Dec 24, 2024 by lamyergeier
@dhiltgen
3
Enhanced aria2c download support with optimized configurations feature request New feature or request
#8203 opened Dec 21, 2024 by A-Akhil
1
StructuredOutputs Schema Missing in Prompt [Unlike OpenAI API Default Behavior] feature request New feature or request
#8162 opened Dec 18, 2024 by ikot-humanoid
Support llama.cpp's Control Vector Functionality feature request New feature or request
#8110 opened Dec 16, 2024 by amyb-asu
3
Add an ollama example that enables users to chat with a code generation model and then tests the code generated by the model feature request New feature or request
#8090 opened Dec 13, 2024 by jagane
ProTip! no:milestone will show everything without a milestone.