Skip to content

Pull requests: auroralabs-loci/llama.cpp

New pull request New
581 Open 153 Closed
581 Open 153 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

UPSTREAM PR #18438: fix: prevent integer overflow in chat template functions
#734 opened Dec 28, 2025 by loci-dev Loading…
UPSTREAM PR #18439: ci: re-enable rocm build on amd64
#733 opened Dec 28, 2025 by loci-dev Loading…
UPSTREAM PR #18441: docker : add CUDA 13.1 image build
#732 opened Dec 28, 2025 by loci-dev Loading…
UPSTREAM PR #18436: CUDA: Blackwell features for non-native builds
#731 opened Dec 28, 2025 by loci-dev Loading…
1
UPSTREAM PR #18431: ggml-cuda: (cmake) expand "native" into concrete architectures
#730 opened Dec 28, 2025 by loci-dev Loading…
1
UPSTREAM PR #18432: android: fix infinite generation in shift_context()
#729 opened Dec 28, 2025 by loci-dev Loading…
1
UPSTREAM PR #18433: ggml-cuda: fixed assertion in ggml_cuda_cpy (#18140, #18341)
#728 opened Dec 28, 2025 by loci-dev Loading…
1
UPSTREAM PR #18426: Revert "ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATI…
#727 opened Dec 28, 2025 by loci-dev Loading…
1
UPSTREAM PR #18422: add in mcp server support to frontend webui [SERVER] [WEBUI]
#726 opened Dec 28, 2025 by loci-dev Loading…
1
UPSTREAM PR #18420: model: add Qwen3-Omni Thinker support (qwen3omnimoe)
#725 opened Dec 28, 2025 by loci-dev Loading…
1
UPSTREAM PR #18415: llama-fit-params: fix step size for last device
#724 opened Dec 27, 2025 by loci-dev Loading…
1
UPSTREAM PR #18416: fix: change llama_chat_apply_template return type from int32_t to int64_t
#723 opened Dec 27, 2025 by loci-dev Loading…
2 tasks done
1
UPSTREAM PR #18413: ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON
#722 opened Dec 27, 2025 by loci-dev Loading…
1
UPSTREAM PR #18412: common: fix return value check for setpriority
#721 opened Dec 27, 2025 by loci-dev Loading…
1
UPSTREAM PR #18410: github: update issue templates [no ci]
#720 opened Dec 27, 2025 by loci-dev Loading…
UPSTREAM PR #18407: ggml-cuda: Use same regex for GGML_NATIVE=OFF
#719 opened Dec 27, 2025 by loci-dev Loading…
1
UPSTREAM PR #18406: mtmd: clarify that we no longer accept AI-generated PRs
#718 opened Dec 27, 2025 by loci-dev Loading…
1
UPSTREAM PR #18401: ggml: add ggml_rope_comp
#717 opened Dec 27, 2025 by loci-dev Loading…
UPSTREAM PR #18400: Fix in the example in examples/retrieval
#716 opened Dec 26, 2025 by loci-dev Loading…
UPSTREAM PR #18399: Add pre-tokenizer hash for MiniMax-M2.1
#715 opened Dec 26, 2025 by loci-dev Loading…
1
UPSTREAM PR #18295: vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron
#714 opened Dec 26, 2025 by loci-dev Loading…
1
UPSTREAM PR #18397: vulkan: disable events for UMA systems to workaround directio failures
#713 opened Dec 26, 2025 by loci-dev Loading…
1
UPSTREAM PR #18391: server : fix crash when seq_rm fails for hybrid/recurrent models
#712 opened Dec 26, 2025 by loci-dev Loading…
1
UPSTREAM PR #18388: (proposal) contributing: tighten AI usage policy
#711 opened Dec 26, 2025 by loci-dev Loading…
1
UPSTREAM PR #18387: rpc: fix segfault on invalid endpoint format
#710 opened Dec 26, 2025 by loci-dev Loading…
6
ProTip! Add no:assignee to see everything that’s not assigned.