Search: “llama-cpp-releases”

ggml: use dynamic allocation for split graph inputs (#22789) ggml: use dynamic allocation for split graph inputs Replace fixed-size GGML_SCHED_MAX_SPLIT_INPUTS arrays with dynamically allocated buffer

vocab : validate default special token ids (#26506) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFra

server: add get_info tool (#26522) server: add get_info tool fix --rpc in docs server: harden get_info probe result handling Report the OS as unknown when the probe process fails to spawn or times out

tests: add model resolution test on synthetic repo listings (#26172) tests: add model resolution test on synthetic repo listings Include download.cpp and arg.cpp inside a namespace with hf_cache monke

model : support MTP in GLM-4.7-Flash (#24868) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework

vendor : update BoringSSL to 0.20260803.0 (#26523) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFram

vendor : update cpp-httplib to 0.52.0 (#26485) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramewor

chat : add new template for DeepSeek V4 Flash 0731 (#26398) common/chat: update DeepSeek V4 templates Align the DeepSeek V4 templates with the official encoders while keeping parser behavior out of th

Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32) (#25874) sycl: extend oneDNN SDPA to Q4_0-Q8_0 and F32 KV caches Extends the oneDNN SDPA path (PR #25222) to handle non-F16 KV cach

sycl: parallelize the non-contiguous concat kernel (#25852) sycl: parallelize the non-contiguous concat kernel Launch geometry only: the non-contiguous concat kernel launched a single-lane work-group

llama : move n_vocab from llama_sampler_data to penalty_sampler (#26520) This matches how it is done for logit_bias and mirostat samplers, see #25262 (comment) Website: https://llama.app macOS/iOS: ma

model : allow reshape of tensors during load (#26531) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCF

vocab : validate plamo2 byte tokens (#26511) validate plamo2 byte tokens --typo Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED

vulkan backend ops: implemented GATED_LINEAR_ATTN (#25601) vulkan : add GATED_LINEAR_ATTN op docs : update Vulkan ops vulkan : remove unused GLA spec constant Updated ops.md ops.md update Website: htt

sync : ggml Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu ar

speculative : refactor enabled configs common_speculative_init (#26510) This commit contains a suggestion to reduce some code duplication in common_speculative_init when adding the enabled speculative

ci: fix pre-built binaries no longer working on macOS 15 and below (#26375) ci: fix pre-built binaries no longer working on macOS 15 and below ci: add macOS deployment target to disabled KleidiAI buil

models : fix dflash wo_a reshape on load (#26577) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFrame

mtmd: support Qwen3-TTS (note: breaking change to llama-tts binary) (#26254) convert text model main model load ok convert encoder ok speaker encoder loading ok speaker enc graph adapt vocab for backb

ui: CWD for agent (#26518) server : extend file_glob_search for UI pickers ui : add per-conversation working directory with picker ui : add path navigation and search scope to cwd picker Treat path-li

sampler : remove 'full-context windows' from history-based samplers (#26524) Resolve -1 to 1024 instead of ctx-len for samplers Because of backend-sampling we initialize samplers before the complete l

mtmd: correcting duplicate empty audio chunks for short inputs (#26536) correcting duplicate empty audio chunks for short inputs tests.sh code restored Website: https://llama.app macOS/iOS: macOS Appl

server: decode Windows OEM output to UTF-8 in built-in tools (#26597) a child process writes in the OEM code page, which is not UTF-8 on a western Windows install, so accented output reaches the JSON

metal: implement DSv4 Lightning Indexer (#25893) metal: implement F16 Lightning Indexer Implement GGML_OP_LIGHTNING_INDEXER for 128-dimensional, 64-head inputs with F32 queries and weights plus F16 ke

llama : MTP support for DeepSeek V3.2 (#26457) llama : MTP support for DeepSeek V3.2 model : no need to include MTP layers during DeepSeek V3.2 model type discovery Co-authored-by: Stanisław Szymczyk

model: MTP support for Qwen3-Next (#25589) mtp for qwen3nex fix for python type-check Fix to compute num_mtp from directly mtp layer define opt_num_mtp_layers in _QwenMtpMixin and fix some comments Fi

server: add notice for upcoming default port change 8080 --> 9931 (#26508) server: add notice for upcoming default port change 8080 --> 9931 add link to PR correct to 9931 Website: https://llama.app m

CUDA: Fix data-races when reusing SMEM in block_reduce (#26385) CUDA: Fix data-races when reusing block_reduce block_reduce currently doesn't resync after reading from SMEM, causing potential data-rac

CUDA: Add backend sampler for penalties sampler (#25262) sampling: enhance penalty handling in common_sampler_init Set default value for penalty_last_n based on model context if not specified. Ensure

llama : allocate indexer cache only in 'full' indexer layers (#26474) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Appl

model: M3: Move MSA into a new memory implementation (#26338) Move MSA logic from llama-kv-cache into llama-kv-cache-msa cont : minor cont : ws fix Co-authored-by: Georgi Gerganov ggerganov@gmail.com

graph : fix unused input tensors in minimax m3 graph (#26519) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)

opencl: route large q6_K lm_head to the flat GEMV (#26427) add a direct size condition for large weights; the original dimension condition is insufficient -- q6_K lm_head for gemma-4 E2B has [1536, 26

ggml-webgpu: add support for f16 repeat (#26307) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramew

model : load MiMo V2 MTP tensors only if used (#26412) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XC

sycl: fix classification of iGPUs (#26105) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Li

chat : add qwen3 specialized parser (#26252) Add tagged thinking tool parser chat : refactor and add permute helper cont : add support for <tool_call> omission cont : update tool delimiters cont : add

DeepseekV4 MTP + DSpark (#25784) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubunt

opencl: bugfix increment ref_count in ggml_backend_opencl_init() (#26162) Incrementing ref_count at the beginning is important later in the free() method of the ggml_backend_opencl_context at program

common: support the DSpark sidecar resolution (#26458) The dspark- files resolve like the other speculative sidecars: the -hfd tag applies to them, a requested sidecar resolves without a full model at

metal: implement DeepSeek V4 hyper-connections (#26459) Implement GGML_OP_DSV4_HC_COMB, GGML_OP_DSV4_HC_PRE, and GGML_OP_DSV4_HC_POST with SIMDgroup register and shuffle optimized kernels. Add Metal d

opencl: limit local workgroup size for GLU operation (#26383) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)

metal : add F16 support for bin ops (#26465) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework

metal : add SILU_BACK (#25982) feat(silu_back): implemented silu_back op for f32 fix(silu_back): removed redundant asserts in ggml-metal-ops.cpp function ggml_metal_op_silu_back. Website: https://llam

chat : enable tool call in thinking for DS4 (#26269) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFr

mtmd: add minicpmv46 downsample (#25993) add minicpmv46 downsample Signed-off-by: tc-mb tianchi_cai@icloud.com put downsample mode inside gguf. Signed-off-by: tc-mb tianchi_cai@icloud.com build mtmd_i