Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
925 Open 10,135 Closed
925 Open 10,135 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

hip: direct alloc for FA f16 temp buffers
#22185 opened Apr 20, 2026 by TheTom Loading…
1
2
Modality conditional adapters examples server testing Everything test related
#22184 opened Apr 20, 2026 by gabe-l-hart Collaborator Loading…
4
Optimize reduction stage of dot product of q4_L/q5_K to q8_K on AVX2 ggml changes relating to the ggml tensor library for machine learning
#22181 opened Apr 20, 2026 by nariox Loading…
vulkan: Support F16 OP_FILL ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#22177 opened Apr 20, 2026 by jeffbolznv Contributor Loading…
1
cuda: disable MMQ stream-k by default for tensor-split MoE ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22174 opened Apr 20, 2026 by nisparks Contributor Loading…
10
fit-params : refactor + add option to output estimated memory per device breaking change Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility. examples server
#22171 opened Apr 20, 2026 by ggerganov Member Loading…
8
ngram-mod: Reset i_last when low acceptance streak occurs
#22168 opened Apr 20, 2026 by treo Loading…
Fix incorrect assertion ggml changes relating to the ggml tensor library for machine learning
#22167 opened Apr 20, 2026 by fiesh Loading…
1
3
common: improve GGUF quantization tag regex
#22164 opened Apr 20, 2026 by v1b3coder Loading…
server: Allow continue in thinking (reasoning prefill) examples server
#22162 opened Apr 20, 2026 by roj234 Contributor Loading…
3
sycl: scalar SWAR byte-subtract in Q6_K MMVQ dot product ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22156 opened Apr 20, 2026 by aicss-genai Loading…
1
server: Support chat_template_kwargs for /v1/messages examples server
#22154 opened Apr 20, 2026 by Soreepeong Loading…
sycl: add GGML_SYCL_USE_ASYNC_MEM_OP env toggle ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22153 opened Apr 20, 2026 by aicss-genai Loading…
1
sycl: Q5_K reorder MMVQ/dequant + Q8_0 reorder MMVQ path ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22152 opened Apr 20, 2026 by aicss-genai Loading…
1
cmake : skip project() when consumed as a subdirectory (#20415) build Compilation issues ggml changes relating to the ggml tensor library for machine learning
#22151 opened Apr 20, 2026 by jinweihan-ai • Draft
4 tasks done
1
1
sycl: route small f32 matmuls to oneMKL, bypass oneDNN ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22150 opened Apr 20, 2026 by aicss-genai Loading…
1
sycl: add FILL, CUMSUM, DIAG, SOLVE_TRI, SSM_SCAN, GATED_DELTA_NET ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22149 opened Apr 20, 2026 by aicss-genai Loading…
1
sycl: support non-contiguous input in PAD op ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22148 opened Apr 20, 2026 by aicss-genai Loading…
1
sycl: Battlemage AOT build via spir64_gen + MMQ subgroup annotations ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22147 opened Apr 20, 2026 by aicss-genai Loading…
1
server : add missing return after validation errors in /infill endpoint examples python python script changes server
#22146 opened Apr 20, 2026 by JoongHyuk-Shin Loading…
server : do not cap slot context to training context (#22140) examples server
#22145 opened Apr 20, 2026 by jinweihan-ai Loading…
3 tasks done
1
1
common : move log to llama-common-base
#22144 opened Apr 20, 2026 by ggerganov Member Loading…
1
vendor : update cpp-httplib to 0.43.1 python python script changes script Script related
#22143 opened Apr 20, 2026 by cabelo Contributor Loading…
CUDA FA: run KV_max mask scan for all Q batch sizes ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22137 opened Apr 20, 2026 by ssam18 Contributor Loading…
1
1
ggml : vectorize Q6_K unpack on WASM SIMD128 (strict, deterministic) ggml changes relating to the ggml tensor library for machine learning
#22134 opened Apr 19, 2026 by Simlowker Loading…
8 tasks done
1
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.