Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
683 Open 8,781 Closed
683 Open 8,781 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

qwen3next : fix chunking model Model specific
#19321 opened Feb 4, 2026 by ggerganov • Draft
vulkan: optimized coopmat matmul perf for IntelGPU ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#19320 opened Feb 4, 2026 by fish-jiang • Draft
1
gguf-py: Bump sentencepiece version python python script changes
#19319 opened Feb 4, 2026 by Ahajha Loading…
2
cleanup llama-quantize --help output examples
#19317 opened Feb 4, 2026 by ddh0 Loading…
1
[WebGPU] Plug memory leaks and free resources on shutdown ggml changes relating to the ggml tensor library for machine learning
#19315 opened Feb 4, 2026 by nikhilJain17 • Draft
4
chore: update cpp-httplib version python python script changes script Script related
#19313 opened Feb 4, 2026 by taronaeo Loading…
1
server: make UI textarea fields resizable examples server
#19312 opened Feb 4, 2026 by ssam18 Loading…
ggml-webgpu: JIT compile binary operators and handle binding overlaps ggml changes relating to the ggml tensor library for machine learning
#19310 opened Feb 4, 2026 by abhijitramesh Loading…
2
vulkan: make FA mask/softcap enables spec constants ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#19309 opened Feb 3, 2026 by jeffbolznv Loading…
sycl: add F16 support for GGML_OP_CEIL 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
#19306 opened Feb 3, 2026 by NechamaKrashinski Loading…
1
vulkan: Set k_load_shmem to false when K is too large ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#19301 opened Feb 3, 2026 by jeffbolznv Loading…
vulkan: fix non-contig rope ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#19299 opened Feb 3, 2026 by jeffbolznv Loading…
1
tests : add non-cont, inplace rope tests testing Everything test related
#19296 opened Feb 3, 2026 by ggerganov Loading…
7
spec: ngram-mod, score-based pruning
#19294 opened Feb 3, 2026 by bfroemel • Draft
1
ci : add metal server workflows devops improvements to build systems and github actions
#19293 opened Feb 3, 2026 by ggerganov • Draft
1 task
CANN: Multi-stream support Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#19284 opened Feb 3, 2026 by hipudding • Draft
@hipudding
Support Step3.5-Flash model Model specific python python script changes
#19283 opened Feb 3, 2026 by forforever73 Loading…
53
[WIP] ggml-hexagon: convert f32 to f16 - fa opt part3 ggml changes relating to the ggml tensor library for machine learning
#19282 opened Feb 3, 2026 by chraac • Draft
1
vulkan: Preprocess FA mask to detect all-neg-inf and all-zero. ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#19281 opened Feb 3, 2026 by jeffbolznv Loading…
3
fix: only reset LoRa configs when they have changed from previous batch examples server
#19280 opened Feb 3, 2026 by agent-enemy-2 Loading…
2
llama : add llama_memory_can_rm_suffix() examples server
#19270 opened Feb 2, 2026 by ggerganov Loading…
1
2
fix: use physical cores for --threads auto-detect (#19110)
#19260 opened Feb 2, 2026 by ingyukoh Loading…
1
1
Add test for vk_buffer from host memory ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#19254 opened Feb 1, 2026 by sredman Loading…
[SYCL] fix segmentation fault on consumer CPUs without bfloat16 hardware ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#19247 opened Feb 1, 2026 by sajonoso Loading…
Feat: Adding token healing support for auto complete examples server
#19238 opened Feb 1, 2026 by agent-enemy-2 Loading…
ProTip! no:milestone will show everything without a milestone.