Skip to content

Pull requests: ollama/ollama

New pull request New
264 Open 3,165 Closed
264 Open 3,165 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

avoid kv truncation during create
#10761 opened May 18, 2025 by dhiltgen Loading…
Add standard OCI image source annotation
#10754 opened May 17, 2025 by AlexGustafsson Loading…
1
fix: cross-domain authentication token exposure
#10750 opened May 16, 2025 by geckosecurity Loading…
Fix SchemaToGrammar having an arbitrary buffer limit breaking some JSON schemas
#10747 opened May 16, 2025 by SchoofsKelvin Loading…
1
3
fix: OpenAI model endpoint (/v1/models/{model}) fails for models with slashes (/) in their name
#10734 opened May 16, 2025 by SplittyDev Loading…
1
docs: add comprehensive documentation structure and guides for Ollama
#10732 opened May 16, 2025 by jonas-eschle Loading…
llm/api/runner: Add ability to generate multimodal embeddings via embeddings endpoints
#10728 opened May 16, 2025 by ajroetker Loading…
1
envconfig: added support for config.env file at ~/.ollama/config.env
#10725 opened May 16, 2025 by davidstevens37 Loading…
1
fix: omit array parsing
#10723 opened May 15, 2025 by mxyng Loading…
remove support for multiple ggufs in a single file
#10722 opened May 15, 2025 by mxyng Loading…
2
ggml: Seperate tensor load from backend creation
#10721 opened May 15, 2025 by jessegross Loading…
feat: qwen3 dense and sparse models
#10708 opened May 14, 2025 by mxyng Loading…
1
Client request hook
#10704 opened May 14, 2025 by linkdata Loading…
llm: Make "POST predict" error message more informative
#10702 opened May 14, 2025 by jessegross Loading…
1
Estimate projector memory correctly for Ollama engine
#10700 opened May 13, 2025 by jessegross Loading…
Give more explicit example on message format
#10697 opened May 13, 2025 by Nubebuster Loading…
Re-remove cuda v11
#10694 opened May 13, 2025 by dhiltgen • Draft
Fix typos
#10683 opened May 13, 2025 by omahs Loading…
4
server/sched.go: Added support for grouping GPUs ( Power-Consumption + Low-PCIe-speed performance gains)
#10678 opened May 12, 2025 by dan-and Loading…
1
Add gfx1200 & gfx1201 support on windows
#10676 opened May 12, 2025 by dhiltgen • Draft
1
Add Huggingface model card README.md (YAML) to GGUF converter
#10634 opened May 9, 2025 by mrutkows Loading…
Update README.md for using Ollama in Microsoft Word locally
#10629 opened May 9, 2025 by GPTLocalhost Loading…
2
Add TensorZero + Ollama guide to README
#10627 opened May 9, 2025 by GabrielBianconi Loading…
server/routes: add GET /health
#10620 opened May 8, 2025 by jrc2139 Loading…
1
docs: recommend manual installs go to /usr/local
#10610 opened May 7, 2025 by strugee Loading…
ProTip! Updated in the last three days: updated:>2025-05-15.