Skip to content

Pull requests: ollama/ollama

New pull request New
822 Open 4,576 Closed
822 Open 4,576 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Model support for batching
#15814 opened Apr 25, 2026 by jessegross Member • Draft
docs: add RDNA4 / gfx1201 ROCm build instructions to development.md
#15811 opened Apr 25, 2026 by LukeLamb Loading…
3 tasks done
5
create: prune imported blobs and startup invalid leftovers
#15809 opened Apr 25, 2026 by stationeros Loading…
fix: improve error handling for model loading in Scheduler
#15808 opened Apr 25, 2026 by famasoon Loading…
Add ollama launch qwen support for Qwen Code CLI
#15805 opened Apr 25, 2026 by B-A-M-N Loading…
launch: add codex model metadata catalog
#15795 opened Apr 24, 2026 by hoyyeva Contributor • Draft
mlx: update to 0.31.2
#15793 opened Apr 24, 2026 by pd95 Loading…
2
Add Atlarix to Code Editors & Development integrations
#15790 opened Apr 24, 2026 by AmariahAK Loading…
sample: implement repeat, frequency, and presence penalties in Go sampler
#15784 opened Apr 24, 2026 by 42euge Loading…
5 tasks done
1
Harden Qwen-family tool payload rendering and fix Qwen 3.5 tool-block truncation integrity
#15774 opened Apr 23, 2026 by B-A-M-N Loading…
cmd: show help when stop and show are called without a model argument
#15773 opened Apr 23, 2026 by anishesg Loading…
1
runner: expose prompt cache hit count in completion response
#15768 opened Apr 23, 2026 by anishesg Loading…
1
3
server: populate parameter_size in /api/tags for safetensors models
#15766 opened Apr 23, 2026 by nandanadileep Loading…
1
docs: add HuggingFace Hub direct GGUF pull pattern to import guide
#15765 opened Apr 23, 2026 by rudi193-cmd Loading…
Prevent system sleep during inference (fixes #4072)
#15763 opened Apr 23, 2026 by ClawdiaHedgehog Loading…
x/mlxrunner/model: add baseline test coverage for quant metadata scanning (supersedes #15745)
#15761 opened Apr 23, 2026 by jodagreyhame Loading…
3 tasks
2
x/mlxrunner: apply config.json per-tensor quant overrides for mixed-precision MoE (supersedes #15744)
#15760 opened Apr 23, 2026 by jodagreyhame Loading…
4 tasks
2
2
x/mlxrunner: recognise mlx-lm plural aux naming at load time (supersedes #15743)
#15759 opened Apr 23, 2026 by jodagreyhame Loading…
3 tasks
2
metal: harden for ggml initialization failures
#15755 opened Apr 22, 2026 by dhiltgen Collaborator Loading…
1
5
app: align the app launch page with ollama launch
#15753 opened Apr 22, 2026 by hoyyeva Contributor Loading…
server: add v2 manifest path
#15735 opened Apr 21, 2026 by pdevine Contributor Loading…
4
fix: resolve OpenClaw gateway launch timeout on Windows by enforcing …
#15726 opened Apr 21, 2026 by UniquePratham Loading…
3
convert: support fp8 safetensors import
#15724 opened Apr 20, 2026 by dhiltgen Collaborator Loading…
Add Spring AI Playground to Chat Interfaces (Desktop)
#15717 opened Apr 20, 2026 by JM-Lab Loading…
server: fix download stall watchdog not firing when no bytes arrive
#15716 opened Apr 20, 2026 by alvinttang Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.