Pull Requests ggml-org/llama.cpp

ggml : add a set of functions for checking contiguity of inner tensor dimensions ggml

#25650 opened 2026-07-14 08:13 by fairydreaming

server : refactor prompt cache state ownership server

#25649 opened 2026-07-14 07:35 by ggerganov

metal : fix null-pipeline crash for F16 src1 mul_mat/mul_mat_id ggml Apple Metal

#25648 opened 2026-07-14 05:33 by QuintinShaw

metal : add F16 support for ADD/SUB/MUL/DIV ggml Apple Metal

#25645 opened 2026-07-14 01:53 by QuintinShaw

common : skip empty implicit default preset

#25643 opened 2026-07-14 01:21 by hogeheer499-commits

convert_hf_to_gguf.py: Refactor how `--mtp` / `--no-mtp` is enabled for a model conversion

#25641 opened 2026-07-14 00:18 by tarruda

opencl: handle OOB write in noshuffle GEMV kernels (odd ne01) testing ggml OpenCL

#25640 opened 2026-07-14 00:12 by wanghqc

opencl: fix a dp4a bug for devices where cl_khr_integer_dot_product is unavailable ggml OpenCL

#25639 opened 2026-07-13 22:56 by wanghqc

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

#25637 opened 2026-07-13 19:44 by ServeurpersoCom

llama : fix null pointer dereference by checking for rotation buffer in K-cache shifts

#25636 opened 2026-07-13 19:44 by engeldlgado

CUDA: XOR swizzle flash attn K,V smem fp16 tiles testing ggml CUDA

#25635 opened 2026-07-13 19:23 by ynankani

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

#25634 opened 2026-07-13 18:41 by bill88t

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

#25631 opened 2026-07-13 17:37 by ServeurpersoCom

cuda: extract Q1_0 elements via __byte_perm ggml CUDA

#25628 opened 2026-07-13 16:01 by dfriehs

requierments: Update in requirements/requirements-compare-llama-bench.txt

#25627 opened 2026-07-13 15:37 by Hemansh2633B

vendor: update BoringSSL to 0.20260713.0 vendor

#25624 opened 2026-07-13 14:36 by cabelo

server : fix 500 bad_function_call on validation errors with X-Conversation-Id (#25605) server

#25623 opened 2026-07-13 13:47 by AmariahAK

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

#25619 opened 2026-07-13 12:24 by ckastner

Test support for alternative conv layout testing ggml CUDA

#25617 opened 2026-07-13 09:15 by pmaybank

mtmd: Unlimited-OCR fix max_tiles, setting in converter mtmd conversion

#25614 opened 2026-07-13 07:32 by sfallah

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

#25613 opened 2026-07-13 06:23 by leonardHONG

server/common : segmentation faults when loading LoRA adapter fails server

#25611 opened 2026-07-13 04:34 by nmouha

sycl: fix UE4M3 parsing ggml SYCL

#25608 opened 2026-07-13 02:17 by clee

security: restrict server CORS to loopback origins server

#25606 opened 2026-07-13 01:42 by macncrash

cuda: Support Q2_0 testing ggml CUDA

#25603 opened 2026-07-12 23:51 by dfriehs

grammar : reject inverted repetition range {m,n} (m>n)

#25602 opened 2026-07-12 22:58 by harrison001

vulkan backend ops: implemented GATED_LINEAR_ATTN documentation Vulkan ggml

#25601 opened 2026-07-12 22:29 by PranavUttarkar

Webui bugfix for single-model mode usage server/ui

#25599 opened 2026-07-12 21:32 by intel00000

gguf : harden loader against malformed tensor dims and metadata types testing ggml

#25596 opened 2026-07-12 21:02 by harrison001

server: fix checkpoint handling for hybrid/recurrent models (#24055) server

#25592 opened 2026-07-12 16:21 by krim404