Search: “apple”

metal : fix idle threads in mul_mv_iq3_xxs for ne00 < 1024 (#28086) metal : fix half-idle simdgroup in kernel_mul_mv_iq3_xxs_f32 for ne00 < 1024 metal : keep N_R0_IQ3_XXS = 4, dispatch a separate 8-ro

server : apply checkpoint min-step eviction only when the checkpoint list is full (#28302) The spacing eviction in create_checkpoint() keeps the oldest checkpoint and erases every later one within che

Revert 'ggml-cuda : restore prop.integrated on HIP builds (#24233)' (#28604) This reverts commit c7d8722. Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/46

llama: disable lazy tensor loading by default on iGPUs (#28326) llama: add lazy mode auto, fix iGPU regression revert changes except disabling lazy load on iGPUs in AUTO Website: https://llama.app Att

vulkan: add TQ1_0 support (mm, mat-vec, mat-vec-id, dequant, get_rows) (#27765) vulkan: add TQ1_0 support (mm, mat-vec, dequant, get_rows) vulkan: pack TQ1_0 powers of 3 into a 32-bit constant Replace

vulkan: rms_norm fusion opportunities (#28024) Support RMS_NORM + MUL + ADD (+ MUL) and RMS_NORM + VIEW + SET_ROWS. Extend ROPE + VIEW + SET_ROWS to support IMROPE. Worth around 4% in gemma4 on my sys

ggml-cuda: fix divergent barrier in f16 flash attention (#27870) ggml-cuda: fix divergent barrier in f16 flash attention ggml-cuda: avoid duplicate metadata pointer setup Website: https://llama.app At

vulkan: support type-aligned GET_ROWS (#28253) vulkan: fall back to CPU for GET_ROWS with misaligned offsets The Vulkan GET_ROWS shader asserts when a tensor's backing-buffer offset plus view_offs is

CUDA: branchless Q4_K/Q5_K unpack to speed up mmvq, L2 prefetch on DGX Spark (#26705) Update Q4_K and Q5_K to use branchless computation, which stops the scale unpack being re-executed for every colum

ggml: add gfx90c HIP support (#26454) ggml: add gfx90c HIP support ggml: make gfx90c HIP support compliant with specifications Website: https://llama.app Attestations: https://github.com/ggml-org/llam

vulkan: add DeepSeek-V4 hyper-connection fused ops (DSV4_HC_COMB/PRE/POST) (#26578) vulkan: add DeepSeek-V4 hyper-connection fused ops (DSV4_HC_COMB/PRE/POST) CUDA has these ops from the DeepSeek-V4 m

tests : initialize the L2_NORM batch array (#28553) tests: bind the L2_NORM batch count to a local GCC cannot prove the loop fills norms up to the index read after it while the bound is a class member

ui : embed assets directly with CMake (#28445) Remove the build-time C++ helper and external gzip dependency, simplifying cross-compilation. Keep the generated C++ in templates for readability and pre

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

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

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

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