Search: “apple”

common: add --log-jsonl (#28437) common: add --log-jsonl rename unknown to none Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45560949 macOS/iOS: macOS Ap

[Model] Support for Spark2_5ForCausalLM implementation (#27868) Add Spark3 Model rename spark3 -> spark2_5 Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co Co-authored-by: dongjiang d

models : fix GDN normalization from max to rsqrt (#28068) models: use flash-linear-attention's l2norm for gated delta net q/k The GDN q/k normalization is defined by flash-linear-attention as l2norm(x

convert : add --fuse-qkv flag to fuse Q/K/V into QKV during HF-to-GGUF conversion (#22780) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45621954 macOS/iO

sycl: attribute device allocations by site (GGML_SYCL_MEMTRACE) (#27631) define two new environment variables to better understand how much memory is being allocated, and when. This has been invaluabl

sycl : fix test-backend-ops CI break && restore Kronecker product FWHT support (#28016) (#28254) Reapply 'sycl : add Kronecker product FWHT support for sizes 384, 640, 768, 12…' (#28184) This reverts

I built a denser GGUF format for ternary models: Q2_B3 / “B3S” If you're running a ternary model like BitNet-b1.58 or Ternary-Bonsai, the weights are already restricted to -1, 0, or +1 times a block s

Also in podcast format New episode: the gripping tale of what is happening in China’s AI companies right now. Are they coming for Open AI and Anthropic? How did they get this good, despite US export c

sycl: fuse rms_norm+mul+add and add+add residual chains (#27610) Fuse RMS_NORM+MUL+ADD and ADD+ADD under GGML_SYCL_ENABLE_FUSION. ADD+ADD uses the same binbcast indexing and type matrix as standalone

src : add n_expert_used_max function (#28323) src : add n_expert_used_max function With Commit c61b98b ('model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444)') it is now poss

ggml-cpu(s390x) : fix q5_1 uninitialized v_acc (#28332) Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45199911

common : make build info output stream configurable (#28322) Let llama_print_build_info write to a caller-provided FILE* instead of hardcoding stderr. The parameter defaults to stderr so existing call

opencl: add Adreno xmem SDPA path (#26331) opencl: add Adreno xmem SDPA path Assisted-by: Codex Removed the Adreno-specific queue profiling override Clean up formatting 修复数值误差优化gqa/mask attn Assisted-

opencl: extend the elementwise and data‐movement op coverage (#27633) opencl: add extended elementwise unary ops (sgn, step, elu, hardswish, hardsigmoid, floor, ceil, round, trunc) Adds nine GGML_UNAR

metal : add remaining fa-vec tunings for M3 (#28396) addition of m3 in fa_vec_tuned_table adding q4_0,q4_1,q5_0,q5_1 in ggml-metal-tuning Fix formatting in ggml-metal-tuning.cpp Website: https://llama

Bloomberg: Sources: Abu Dhabi-based AI company G42 is exploring selling a majority stake to US companies, hoping to safeguard access to advanced AI chips beyond April 2027 — Executives at Abu Dhabi-ba

AI enhanced journaling is changing my life I've been running a Wispr Flow + Claude Cowork workflow that turns rambles into structured data and action items Super simple setup: 1. After meetings/events

mtmd: add mtmd_tokenize_from_parts() (#28250) add mtmd_tokenize_from_parts use it in mtmd-cli move add_special to call level Website: https://llama.app Attestations: https://github.com/ggml-org/llama.

ggml-hexagon: add F16 support for unary ops (#28228) Extend the HTP backend's F16 unary op coverage to include ABS on top of the existing NORM/RMS_NORM/L2_NORM/SCALE/CLAMP/SQR/SQRT set. Add hvx_abs_f1

server : accept data: URLs for input_video and input_audio (#27735) server : accept data: URLs for input_video and input_audio input_video and input_audio passed accept_base64_uri=false to handle_medi

finetune: fix no KV cache (#27199) training: fix no KV cache apply @ ggerganov suggestion Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44871971 macOS/iOS

model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444) hparams: add per-layer n_ff_exp/n_expert_used arrays with scalar-or-array loading G1/G2 infrastructure for variable-per-l

sycl: reduce redundant work in Q4_K multi-column MMVQ (#27062) sycl: Q4_K Weight unpack optimization and reuse between destination Columns sycl: Q4_K small N (N=2..4) + two output rows by subgroup reu

vulkan: fix FA dequant path engagement (#28190) Skip the nb[3] check when ne[3] == 1, the shader never reads it for a single stream. Cache views carry the full-buffer stride there, so the old check re

CUDA: Allow concurrent streams per split for multi-GPU (#28198) CUDA: Allow CUDA optimization per split for multi-GPU. Previous guard caused multi-GPU to skip the graph optimization. The graph is alre

mtmd : add const in various places (#28307) mtmd : mark context as const in more methods Mark mtmd_context as const in: mtmd_bitmap_init_lazy mtmd_tokenize mtmd_tokenize_from_parts mtmd_helper_support

metal : fix glu dispatch with ne00 = 1 (#28306) metal : fix glu dispatch with ne00 = 1 tests : disable ill-defined tests Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/

metal : add sparse FA (#28098) metal : support n_kv_max sparse mask hint in flash attention vec kernel add kernel_flash_attn_ext_vec_idx: compacts finite mask entries into a per-row index list (Hillis

opencl: quant lm_head / decode GEMV and medium-batch GEMM optimizations (speculative decoding/MTP) (#26477) opencl: quant lm_head / decode GEMV and medium-batch GEMM optimizations opencl: guard q4_K/q

common/json-schema : fix GBNF grammar generation for empty object schemas (#28279) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45102223 macOS/iOS: macOS

Quality: 81.1 → 87.7 (+8%) Speed: 35 → 29 tok/s (−16%) Runtime: 8m51s → 44m39s (5x longer) Output tokens: 18K → 78K (🤯) Noticeably better quality, but you're paying for it with tokens and time. Full b

hexagon: add missing FARF logs for cpy/get_rows/set_rows/gdn ops (#28217) hexagon: fix bug ne[2] printed in proc_op_req prep-src log hexagon: add shape/VTCM farf logs to cpy, get/set rows, gdn Website

opencl: fix out‐of‐bound reads in the Adreno image kernels (#27632) opencl: clamp the q4_K decode GEMV's fetch row on a padded x-grid opencl: enforce the tiling contract of the image KQ/KQV GEMMs open

vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec (#27449) vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec when NUM_COLS > 4. 5x perf at n=8 Assisted-by: Claude

hexagon: MUL_MAT and MUL_MAT_ID fusion and fixes (#28202) hex-mm: fuse QKV and FFN matmuls that land on HMX hex-mm: remove hardcoded ne[1] < 32K restriction hex-get-rows: explicitly reject repacked Q8

ggml: avoid KleidiAI buffer type init on dispatch (#27891) Co-authored-by: Acmmi acmmi@Acmmis-MacBook-Air.local Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestati

mtmd: Fix Qwen3-tts-0.6b (#28231) mtmd: load the qwen3-tts code predictor proj_in as optional The talker and the code predictor share the hidden size on the 0.6B checkpoints, so the reference builds n

mtmd: support DeepSeek-V4-Flash-Vision-Exp (#28133) mtmd: support DeepSeek-V4-Flash-Vision-Exp handle min/max token counts from CLI rm debugging use GGML_ROPE_TYPE_VISION nits apply review comments co

common, server : enable preserve_reasoning kwarg by default, log its effective state (#28174) common, server : enable preserve_reasoning kwarg by default, log its effective state If the preserve_reaso

ggml-cuda : remove unused vars (#28235) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44811308 macOS/iO

model: correctly support input vision for deepseek4 (#28154) model: correctly support input vision for deepseek4 nits Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/att

metal : fix memory query under low-memory conditions (#27701) metal: Fix memory query under low-memory conditions Simply variable name Co-authored-by: Georgi Gerganov ggerganov@gmail.com Write it even

We benchmark Qwen3.6-35B-A3B on an M5 Max MacBook Pro. Across ten prompt lengths and ten decode contexts, Lily was faster than MLX-LM, averaging 1.23× higher prefill throughput and 1.35× higher decode

qwen4exp: sum the indexer heads by slices (#28023) qwen4exp: sum the indexer heads by slices The head reduction went through a transpose and a sum_rows over ne[1], which left sum_rows with ne0 = 4, on

qwen4exp: support recurrent state rollback (#28123) MTP speculative decoding needs the target state to move back by the number of rejected draft tokens. Without rollback support the context is classif

metal: enable Metal 4.0 tensor API on M5+/A19+ (#27461) metal : request Metal 4.0 language version for the tensor API metal : load the tensor API kernels from a separate metallib tests : add external-