Pull Requests ggml-org/llama.cpp

ui: fix thinking menu never appearing in single-model mode server/ui

#25637 by ServeurpersoCom was merged 2026-07-15 11:39

Fix missing space in tool-call prompt request server/ui

#25634 by bill88t was merged 2026-07-14 15:23

CUDA: add GGML_OP_LIGHTNING_INDEXER kernel (F16/F32 K) ggml CUDA

#25632 by Dorijan10 was closed 2026-07-14 02:43

ui: fix mcp panel for toggle + timeout + proxy + ON/OFF state server/ui

#25631 by ServeurpersoCom was merged 2026-07-14 14:50

Re-add the llama-proxy toggle in the "Add New Server" menu & fix the missing space in tool-call requests server/ui

#25630 by bill88t was closed 2026-07-13 18:03

readme : add link to maintainer PRs documentation

#25621 by ggerganov was merged 2026-07-13 13:07

tests: export-graph-ops: exit gracefully when called w/o arguments testing

#25619 by ckastner was merged 2026-07-14 10:15

tests: Harmonize header use testing merge ready

#25616 by ckastner was merged 2026-07-13 12:36

CUDA: tighter MMQ src1 buffer size for native fp4 ggml CUDA

#25613 by leonardHONG was merged 2026-07-15 15:21

ppu: dlopen .so seam for FA / MoE-GEMM / gated-delta-net CUDA kernels documentation testing ggml CUDA

#25607 by DrXuQian was closed 2026-07-13 01:59

Fix Minimax 2 EAGLE3 support model merge ready

#25604 by adrianisk was merged 2026-07-13 13:22

Webui bugfix for single-model mode usage server/ui

#25599 by intel00000 was closed 2026-07-14 09:45

Withdrawn

#25597 by harrison001 was closed 2026-07-12 21:31

model : add Laguna (poolside Laguna-XS-2.1) support model conversion

#25595 by jtmuller5 was closed 2026-07-12 18:59

server: Don't consider models with --no-mmproj-auto as multimodal server

#25590 by sdroege was merged 2026-07-12 22:48

DeepseekV4: fix seq_rm

#25588 by am17an was merged 2026-07-14 13:45

HIP: Tune RDNA4 MMQ tiles for Q6_K / Q2_K (gfx1201) ggml CUDA

#25587 by qiongz was closed 2026-07-12 16:56

vulkan : add support for f16->f16 GGML_OP_SET_ROWS Vulkan ggml

#25581 by fairydreaming was closed 2026-07-12 16:10

CUDA: allow small_k mmvq for IQ3 types when K is too small to occupy the block testing ggml CUDA

#25578 by giannisanni was closed 2026-07-12 05:13

vendor : update cpp-httplib to 0.50.0 and 0.50.1 vendor

#25576 by cabelo was merged 2026-07-12 23:10

vendor : update cpp-httplib to 0.50.0 vendor

#25572 by cabelo was closed 2026-07-12 01:54

Added support of MTP speculative decoding on zai/glm-4.7-flash model conversion

#25564 by TriDefender was closed 2026-07-12 11:24

Improve code quality, documentation, and build system documentation build server ggml mtmd OpenVINO conversion

#25561 by ghshhf was closed 2026-07-11 21:18

ui: Unify tool activation on the MCP override model and make it syncable server/ui

#25559 by ServeurpersoCom was closed 2026-07-13 07:54

feat(ggml-cpu): add VLEN1024 Q4_K/Q5_K 64x1 CPU_REPACK path ggml

#25553 by muggle-stack was closed 2026-07-15 09:12

[SYCL] Support OP XIELU documentation ggml merge ready SYCL

#25550 by atsmith3 was merged 2026-07-15 07:29

mtmd: fix silent prompt truncation on embedded NUL server mtmd

#25548 by ServeurpersoCom was merged 2026-07-12 22:47

cuda : CUDA GGML_OP_LIGHTNING_INDEXER implementation (generic vector kernel + wmma kernel) ggml CUDA

#25545 by fairydreaming was merged 2026-07-15 17:57

server: refactor server_stream documentation server merge ready

#25541 by ngxson was merged 2026-07-11 10:41

ui: add reasoning effort control to mobile add sheet server/ui

#25539 by ServeurpersoCom was merged 2026-07-14 10:05