Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
925 Open 10,250 Closed
925 Open 10,250 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

common/gemma4 : fix multi-turn tool call parsing with literal <|tool_call> in content testing Everything test related
#22367 opened Apr 25, 2026 by arkavo-com Contributor • Draft
Convert argv from UTF-16 on Windows for non-ASCII -p prompts examples
#22366 opened Apr 25, 2026 by duzenko Loading…
1
[Tensor Parallel] Fix recurrent state serialization for partial reads and writes ggml changes relating to the ggml tensor library for machine learning
#22362 opened Apr 25, 2026 by gaugarg-nv Contributor Loading…
Add DeepSeek V4 GGUF conversion python python script changes
#22359 opened Apr 25, 2026 by nisparks Contributor Loading…
5
convert : support input_scale for fp8 modelopt python python script changes
#22356 opened Apr 25, 2026 by CISC Member Loading…
1
ggml : revert to -lm linking instead of find_library ggml changes relating to the ggml tensor library for machine learning
#22355 opened Apr 25, 2026 by angt Member Loading…
1
rpc: add ipv6 support examples ggml changes relating to the ggml tensor library for machine learning
#22350 opened Apr 25, 2026 by alphaonex86 Loading…
fix: read n_embd before vocab_only early return for mmproj init
#22348 opened Apr 25, 2026 by ChenYFan Loading…
6
hexagon: hmx flash attention ggml changes relating to the ggml tensor library for machine learning Hexagon testing Everything test related
#22347 opened Apr 25, 2026 by njsyw1997 Contributor • Draft
2
ggml-cpu: optimize avx2 q6_k ggml changes relating to the ggml tensor library for machine learning merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge.
#22345 opened Apr 25, 2026 by netrunnereve Collaborator Loading…
ggml-webgpu: fast matrix-vector multiplication for i-quants ggml changes relating to the ggml tensor library for machine learning WebGPU
#22344 opened Apr 25, 2026 by SharmaRithik Loading…
chat: preserve media markers for typed-content templates
#22342 opened Apr 25, 2026 by AlexonOliveiraRH Loading…
2 tasks done
1
ggml: implement gguf_init_from_buffer ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#22341 opened Apr 24, 2026 by giladgd Contributor Loading…
3
common: fix missing exports in llama-common
#22340 opened Apr 24, 2026 by max-krasnyansky Member Loading…
2
cpu : re-enable fast gelu_quick_f16 ggml changes relating to the ggml tensor library for machine learning merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge.
#22339 opened Apr 24, 2026 by CISC Member Loading…
server: respect per-request enable_thinking toggle via extra_body examples server
#22336 opened Apr 24, 2026 by pju-hoge Loading…
2
opencl: refactor Adreno q4_0 ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#22335 opened Apr 24, 2026 by lhez Contributor • Draft
ggml-webgpu: silence subgroup_uniformity diagnostic in mul_mat_vec ggml changes relating to the ggml tensor library for machine learning WebGPU
#22332 opened Apr 24, 2026 by SharmaRithik Loading…
3
ggml-cpu: optimize q8 quantization on x86 SIMD ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#22331 opened Apr 24, 2026 by bitRAKE Contributor Loading…
CUDA: better coalesce data-access for contiguous concat ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22330 opened Apr 24, 2026 by ORippler Collaborator Loading…
llama-bench: fix numerical instability in stdev() calculation examples
#22329 opened Apr 24, 2026 by abhinavuser Loading…
1
1
Update server README.md to clarify cache directory choice behavior examples server
#22328 opened Apr 24, 2026 by de1eted-user Loading…
Update README.md to add AI Playground to the UI list
#22326 opened Apr 24, 2026 by qiacheng Loading…
Fix gemma4 prefill parsing
#22325 opened Apr 24, 2026 by Quairon-Nailo Loading…
1
common : re-arm reasoning budget after DONE on new <think> testing Everything test related wontfix This will not be worked on
#22323 opened Apr 24, 2026 by BruceJillis Loading…
8
ProTip! Updated in the last three days: updated:>2026-04-22.