Commit History

Author SHA1 Message Date
  Georgi Gerganov 374fe09cdd ggml : use std::sort in ggml_argsort CPU implementation (#17211) 2 months ago
  Aleksander Grygier 8e878f0cb4 Update packages + upgrade Storybook to v10 (#17201) 2 months ago
  Xuan-Son Nguyen 00c94083b3 server: (refactor) implement generator-based API for task results (#17174) 2 months ago
  Xuan-Son Nguyen 017eceed61 ci: add check vendor job (#17179) 2 months ago
  Xuan-Son Nguyen ee8dd5c658 server: move res_error/res_ok to static function (#17167) 2 months ago
  Alberto Cabrera Pérez 1c398dc9ec ggml-cpu: handle 3d tensors in repack mat_mul (#17030) 2 months ago
  Adrien Gallouët 52cf111b31 cmake : cleanup (#17199) 2 months ago
  Adrien Gallouët 78010a0d52 cmake : move OpenSSL linking to vendor/cpp-httplib (#17177) 2 months ago
  TecJesh 655cddd174 CANN: Add L2_NORM op support (#16856) 2 months ago
  Neo Zhang Jianyu 5da7664960 [SYCL]fix ci crash about SSM_CONV (#17169) 2 months ago
  Raul Torres 23a46ce972 CANN: GGML_CANN_ACL_GRAPH works only USE_ACL_GRAPH enabled (#16861) 2 months ago
  Max Krasnyansky c273d75375 hexagon: various Op fixes (#17135) 2 months ago
  Eve 7d019cff74 disable rms norm mul rope for chips with no fp16 rte (#17134) 2 months ago
  sudhiarm 3fe36c3238 ci: add Arm-hosted Graviton4 runner (#17021) 2 months ago
  Xuan-Son Nguyen 1d45b4228f vendor: split httplib to cpp/h files (#17150) 2 months ago
  ixgbe ca4844062b ggml-cpu : add RISC-V RVV (Zvfh) optimization for FP16 to FP32 conversion (#17161) 2 months ago
  duduta 73460f6278 ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 (#16805) 2 months ago
  Charles Xu 8c583242ad kleidiai: add optimized per-channel kernels for Q8_0 (#16993) 2 months ago
  Mike Abbott 4a5b8aff40 cmake : add version to all shared object files (#17091) 2 months ago
  Nicolas B. Pierron d2d626938a Install rpc-server when GGML_RPC is ON. (#17149) 2 months ago
  levkropp 2fc392ce35 convert : register UMT5Model architecture for T5 conversion (#17160) 2 months ago
  lhez ece0f5c177 opencl: add fastdiv and use it in set_rows, ported from cuda (#17090) 2 months ago
  Sigbjørn Skjæret 7bef684118 models : move build_inp_out_ids outside loop (#17151) 2 months ago
  Max Krasnyansky 395e286bc9 cpu: skip NOPs to avoid barriers (#17133) 2 months ago
  Georgi Gerganov 13730c183b metal : cap threadgroups size of set_rows (#17146) 2 months ago
  Adrien Gallouët 967eb4b2bf ggml-cpu : inspect -march and -mcpu to found the CPU (#16333) 2 months ago
  Ruben Ortlam f117be185e vulkan: check glslc executable string (#17144) 2 months ago
  Ruben Ortlam 85234a4b3a vulkan: fix validation issue introduced by #16868 (#17145) 2 months ago
  Gabe Goodhart 0c74f32632 memory: Hybrid context shift (#17009) 2 months ago
  Georgi Gerganov c27efd2bd1 metal : enable tensor API for A19 (#17087) 2 months ago