Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
1,102 Open 11,290 Closed
1,102 Open 11,290 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

CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#24546 opened Jun 12, 2026 by ravel7524 Contributor Loading…
docs: add eagle3 to speculative doc documentation Improvements or additions to documentation
#24540 opened Jun 12, 2026 by LiaXLiang Loading…
spec: add spec metrics mean acceptance length and acceptance rate per position examples server
#24536 opened Jun 12, 2026 by ruixiang63 Contributor Loading…
@ggerganov
1
ggml cpu: Improve dequantize vectorisation for q4, q5 ggml changes relating to the ggml tensor library for machine learning
#24535 opened Jun 12, 2026 by mkj Loading…
CUDA: only support F32/F16 for GGML_OP_REPEAT ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#24533 opened Jun 12, 2026 by leonardHONG Contributor Loading…
ggml-webgpu: improve i-quants mul_mat performance and speed up prefill ggml changes relating to the ggml tensor library for machine learning WebGPU
#24530 opened Jun 12, 2026 by yomaytk Contributor Loading…
1
fix sycl links in release notes devops improvements to build systems and github actions
#24527 opened Jun 12, 2026 by muhammad-salem Loading…
2
cuda : fix flash attention crash for d_head=512 with gqa_ratio=2 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#24526 opened Jun 12, 2026 by nhs000 Contributor Loading…
1
Preliminary MiniMax-M3 support model Model specific python python script changes testing Everything test related
#24523 opened Jun 12, 2026 by danielhanchen Contributor • Draft
5
fit : wrap llama_device_memory_data examples server
#24522 opened Jun 12, 2026 by ggerganov Member Loading…
server : unify mtmd image processing with post-decode callback examples server
#24520 opened Jun 12, 2026 by ggerganov Member • Draft
1 task done
2
bench : add --offline examples python python script changes server
#24511 opened Jun 12, 2026 by angt Member Loading…
opencl: optimize mul_mat_f16_f32 for decode ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#24504 opened Jun 12, 2026 by lhez Contributor • Draft
openvino: OV 2026.2, context-shift, Q5_1 support, gemma4 dense/embedding, and -fa off devops improvements to build systems and github actions documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning OpenVINO
#24503 opened Jun 12, 2026 by wine99 Contributor Loading…
1 task done
1
UI : fix SSE transport detection and routing through CORS proxy. Assi… examples server/ui
#24500 opened Jun 12, 2026 by hrpnr Loading…
2
server : reset fit_params_target to baseline on model (re)load examples server
#24498 opened Jun 12, 2026 by liminfei-amd Loading…
1 task done
1
1
common: add sampling env vars examples server
#24494 opened Jun 11, 2026 by Abrosimov-a-a Loading…
ggml: Update VMM Pool allocation ggml-cuda.cu - Turing P2P access fix (fixes #24489) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#24491 opened Jun 11, 2026 by VexxieCode Loading…
1
2
common: update logging to enforce max_capacity and optimize queue resizing
#24490 opened Jun 11, 2026 by max-krasnyansky Member Loading…
2
CUDA: Fuse MMVQ post-scale for NVFP4 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#24481 opened Jun 11, 2026 by ORippler Collaborator Loading…
[SYCL] add dev2dev memcpy by SYCL API documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#24476 opened Jun 11, 2026 by arthw Contributor Loading…
fix(hexagon): use padded stride for ssm-conv weights ggml changes relating to the ggml tensor library for machine learning Hexagon
#24470 opened Jun 11, 2026 by BiReRa Loading…
1
docs(server): add llama-server WebUI settings complete guide documentation Improvements or additions to documentation
#24467 opened Jun 11, 2026 by xusk999 Loading…
1
docs : fix typos in CUDA-FEDORA.md and grammars/README.md documentation Improvements or additions to documentation
#24459 opened Jun 11, 2026 by m-atharkhan Loading…
1
ggml: improve RVV q4_0 GEMM prefill locality ggml changes relating to the ggml tensor library for machine learning
#24456 opened Jun 11, 2026 by ZephyrLi-pro Loading…
ProTip! What’s not been updated in a month: updated:<2026-05-12.