Pull Requests ggerganov/llama.cpp

server: Improve get_datetime tool to return structured ISO-8601 JSON examples server

#22843 opened 2026-05-08 15:29 by yamc12

ggml: fixed Arm SVE usage bug in vec.h, vec.cpp ggml

#22841 opened 2026-05-08 14:36 by martin-klacer-arm

spec : parallel drafting support examples server

#22838 opened 2026-05-08 12:44 by ggerganov

ggml-cpu : add STQ1_0 ternary quantization with ARM NEON vec_dot kernel examples python ggml

#22836 opened 2026-05-08 11:07 by sjl623

convert_hf_to_gguf: fix Qwen3.5 linear_num_value_heads overridden by AutoConfig defaults python

#22835 opened 2026-05-08 10:56 by LucaSforza

ggml : add ggml_conv_1d_grouped testing ggml

#22833 opened 2026-05-08 10:15 by Juste-Leo2

convert : add split() to LoraTorchTensor in LoRA converter testing python

#22832 opened 2026-05-08 08:42 by jesus-talavera-ibm

webui: support video files as input server/webui examples server

#22830 opened 2026-05-08 07:49 by foldl

server: preserve context checkpoint coverage examples server

#22826 opened 2026-05-08 00:53 by jacekpoplawski

Feature hexagon tri ggml Hexagon

#22822 opened 2026-05-07 20:48 by pdhinaka

HIP: Adds 4x packed Q8_1 activation for Q4_K_M models in MMVQ Nvidia GPU ggml

#22821 opened 2026-05-07 20:45 by jiachengjason

ggml-webgpu: address precision issues for multimodal ggml WebGPU

#22808 opened 2026-05-07 16:57 by Constannnnnt

Add new config file options for saving and loading configuration for llama tools in INI format

#22802 opened 2026-05-07 13:04 by bartowski1182

webui: page title use app name variable server/webui examples server

#22801 opened 2026-05-07 12:58 by jpm-canonical

mtmd-cli: load GPU backends before arg parsing to fix false 'no GPU' warning examples

#22790 opened 2026-05-07 09:07 by saga08003137

ggml: use dynamic allocation for split graph inputs ggml

#22789 opened 2026-05-07 09:02 by AgoraPete

spec : refactor ctx examples python server ggml Apple Metal

#22787 opened 2026-05-07 06:55 by ggerganov

convert : add `--fuse-qkv` flag to fuse Q/K/V into QKV during HF-to-GGUF conversion model python

#22780 opened 2026-05-07 02:24 by JoursBleu

ggml-sycl : use malloc_shared for UMA/integrated GPU devices ggml SYCL

#22766 opened 2026-05-06 15:11 by vmartirosyan

Draft: ggml-opencl: Early proof-of-concept implementation of plans via command buffers ggml OpenCL

#22764 opened 2026-05-06 14:20 by jansol

android: extract GgufMetadataReader factory to break cyclic dependency android examples

#22763 opened 2026-05-06 14:12 by Juste-Leo2

server: fix /infill prompt placement after FIM_MID examples server

#22761 opened 2026-05-06 13:30 by Aayush7g

ggml-opencl: add opt-in Adreno xmem F16xF32 GEMM for prefill ggml OpenCL

#22755 opened 2026-05-06 11:42 by happyyzy

ggml-cpu: extend RVV quantization vec dot to higher VLENs ggml

#22754 opened 2026-05-06 10:45 by rehan-10xengineer

Add more wav-compatiable MIME types and enhance MIME type normalization server/webui examples server

#22744 opened 2026-05-06 04:08 by guangchenli

webui : [ChatFormActionAdd][a11y] fix accessibility issues in add menu trigger and items server/webui examples server

#22736 opened 2026-05-06 01:41 by vignesh191

llama : extend embeddings API model

#22728 opened 2026-05-05 17:55 by ggerganov

server, webui: support continue generation on reasoning models server/webui examples server

#22727 opened 2026-05-05 17:15 by ServeurpersoCom

Filter tools openai server task examples server

#22725 opened 2026-05-05 15:57 by sonic182

Adding support for the granite multilingual embeddings R2 (ibm-granite/granite-embedding-{97,311}m-multilingual-r2 models) model python

#22716 opened 2026-05-05 13:48 by hansolosan