Skip to content

Pull requests: ollama/ollama

New pull request New
983 Open 4,798 Closed
983 Open 4,798 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

llm: fix ollama ps double-counting mmap'd weights on partial offload
#16709 opened Jun 13, 2026 by discobot Loading…
1
2
cmd/interactive.go: convert "true"/"false" strings to bools in /set think
#16705 opened Jun 13, 2026 by guntherdoescode Loading…
llm: allow MMProj offload for CUDA on integrated GPUs
#16703 opened Jun 13, 2026 by wu-zuan Loading…
discover: allow gfx1150 (RDNA 3.5) integrated GPU by default
#16701 opened Jun 13, 2026 by liminfei-amd Loading…
1
fix(parsers/qwen3coder): recover bare <function=...> tool call when opening <tool_call> tag is omitted
#16693 opened Jun 12, 2026 by Anai-Guo Loading…
1
Add num_cpu_moe option to keep MoE expert tensors on the CPU (pass through llama-server --n-cpu-moe)
#16688 opened Jun 12, 2026 by Verma-Rajat Loading…
2
1
server: truncate embedding inputs to the physical batch size
#16687 opened Jun 12, 2026 by discobot Loading…
1
llm: warn when model silently falls back to CPU despite GPU being available
#16684 opened Jun 12, 2026 by nac7 Loading…
Restructure file-path regex pattern to explicitly traverse directory boundaries
#16681 opened Jun 11, 2026 by dstadulis Loading…
1
llama: update llama.cpp version to b9592
#16672 opened Jun 11, 2026 by rejzzzz Loading…
1
models: add Cohere2MoE model model Model requests
#16670 opened Jun 11, 2026 by jmorganca Member Loading…
7
discover: fix inverted iGPU/dGPU Vulkan classification on Windows hybrid graphics
#16669 opened Jun 11, 2026 by Sahil170595 Loading…
1
1
readme: add ollmcp to community integrations
#16666 opened Jun 10, 2026 by jonigl Loading…
docs: add missing fields to /api/tags example response
#16665 opened Jun 10, 2026 by veeso Loading…
convert: read top-level text fields for text-only gemma4 configs
#16663 opened Jun 10, 2026 by HYUEHFJKhfjklkej Loading…
1
x/mlxrunner: validate affine quant params against packed tensor shapes
#16661 opened Jun 10, 2026 by HYUEHFJKhfjklkej Loading…
feat(cache): write CACHEDIR.TAG into the models directory
#16660 opened Jun 10, 2026 by Anai-Guo Loading…
1
4
docs: add Sieve to community integrations (RAG & Knowledge Bases)
#16655 opened Jun 9, 2026 by azardhosein Loading…
launch: Add VS Code extension launch flow
#16653 opened Jun 9, 2026 by hoyyeva Contributor • Draft
fix: Audio only projector without vision capability
#16651 opened Jun 9, 2026 by gabe-l-hart Contributor Loading…
12
Fix macOS installer app launch path
#16640 opened Jun 9, 2026 by BeauDevCode Loading…
1
server: validate safetensors architecture before copying blobs
#16630 opened Jun 8, 2026 by nac7 Loading…
1
1
progress: fix data races on ticker and states fields
#16629 opened Jun 8, 2026 by nac7 Loading…
1
1
jetson: add CC 87 for CUDA v13
#16628 opened Jun 8, 2026 by dhiltgen Collaborator Loading…
docs: add pi.dev AI refactoring tldr
#16627 opened Jun 8, 2026 by dst0 Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.