Commit History

Author SHA1 Message Date
  Jeff Bolz 3229a23fa6 vulkan: support GGML_OP_DIAG (#17893) 1 month ago
  Jeff Bolz 303f8615e9 vulkan: Multi-pass softmax for large number of cols (#17892) 1 month ago
  Jeff Bolz 07a10c1090 vulkan: Allow non-pow2 n_experts in topk_moe (#17872) 1 month ago
  Jeff Bolz db97837385 vulkan: perf_logger improvements (#17672) 1 month ago
  Phylliida Dev 09c7c50e64 ggml : add circular tiling support to pad, for Vulkan, CUDA, and CPU (used for making seamless textures) (#16985) 1 month ago
  Jeff Bolz 2960eb2975 vulkan: Use one row per workgroup for f32 mmv (#17711) 1 month ago
  Jeff Bolz c6c5e85979 vulkan: support solve_tri with larger N/K values (#17781) 1 month ago
  Masato Nakasaka 67788f6846 vulkan: Replace deprecated VK_EXT_validation_features (#17637) 1 month ago
  Masato Nakasaka d8c0a7b085 vulkan: Fix mismatch in TOPK_MOE unit test (#17541) 1 month ago
  Jeff Bolz a0f3897d53 vulkan: fix top_k bug when there are ties in the input (#17659) 1 month ago
  Acly e15cd06a94 vulkan : support conv-2d with large output size (#17685) 1 month ago
  Jeff Bolz 6ab0d64960 vulkan: enable mmvq for q2_k on NVIDIA (#17675) 1 month ago
  Jeff Bolz 93bb92664e vulkan: set all memory allocations to high priority (#17624) 1 month ago
  Jeff Bolz 61bde8e21f vulkan: Reduce temporary memory usage for TOP_K (#17623) 1 month ago
  Tarek Dakhran 2ba719519d model: LFM2-VL fixes (#17577) 1 month ago
  Ruben Ortlam 47a268ea50 Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support (#16900) 1 month ago
  Jeff Bolz 59d8d4e963 vulkan: improve topk perf for large k, fix overflow in unit tests (#17582) 1 month ago
  Jeff Bolz 35cf8887e1 vulkan: Implement GGML_OP_TRI (#17503) 1 month ago
  Jeff Bolz 4abef75f2c vulkan: Implement SOLVE_TRI (#17486) 2 months ago
  Acly b78db3bd50 vulkan : move contiguous checks to device_supports_op (#17490) 2 months ago
  Jeff Bolz 142df17c9c vulkan: use a fixed 1KB buffer for the add_rms_fusion opt (#17514) 2 months ago
  Jeff Bolz eec1e33a9e vulkan: allow graph_optimize for prompt processing workloads (#17475) 2 months ago
  Jeff Bolz 879d673759 vulkan: Implement top-k (#17418) 2 months ago
  Jeff Bolz b3b03a7baf vulkan: Implement GGML_OP_CUMSUM (#17479) 2 months ago
  Jeff Bolz d414db02d3 vulkan: Use fewer rows for scalar FA when HS is not a multiple of 16 (#17455) 2 months ago
  Jeff Bolz 3d07caa99b vulkan: more FA details in vk_perf_logger (#17443) 2 months ago
  Jeff Bolz 54d83bbe85 vulkan: remove a couple unnecessary switches (#17419) 2 months ago
  Jeff Bolz f1ffbba68e vulkan: disable async for older Intel devices (#17369) 2 months ago
  Giuseppe Scrivano 7d77f07325 vulkan: implement ADD1, ARANGE, FILL, SOFTPLUS, STEP, ROUND, CEIL, FLOOR, TRUNC (#17319) 2 months ago
  Jeff Bolz 1fa4551af0 vulkan: support larger argsort (#17313) 2 months ago