b10080
server: return 400 instead of 500 on validation error with X-Conversation-Id (#25760) server: return 400 instead of 500 on validation error with X-Conversation-Id set_req() attaches the…
Latest
b10088
llama-arch: fix DeepSeek4 APE tensor op (#25945)
b10079
server : properly handle null llama_context (#25868) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…
b10078
vulkan: Refactor vk_queue to use per-instance mutexes and unique handles (#23570) Refactor vk_queue to use per-instance mutexes and unique handles integrates VK_KHR_internally_synchronized_queues, abstracting the queue submission…
b10077
ggml-openvino: Add GGML_BACKEND_DL_IMPL invocation for OpenVINO backend (#25795) This adds the missing GGML_BACKEND_DL_IMPL() macro invocation, that other backends have. Fixes #25586 for me Website: https://llama.app macOS/iOS:…
b10076
CUDA: vectorize same-type get_rows with int4 copy (#25929) k_get_rows_float did a scalar one-element-per-thread copy and recomputed the row-invariant work (index load, fast_div_modulo, src/dst row pointers) for…
b10075
hexagon: add CLAMP op (#25934) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu…
b10069
opencl: Support broadcast for Adreno MUL_MAT and honor view_offs for Adreno Q8_0 MUL_MAT for llama-server multi-stream (#25910) opencl: handle broadcast for adreno gemm/gemv_noshuffle opencl: honor view_offs…
b10068
model: rotate injected K/V cache for DFlash (#25823) dflash: rotate injected K/V cache when using K/V quantization Update src/models/dflash.cpp Co-authored-by: Georgi Gerganov ggerganov@gmail.com clearer format remove…
b10067
llama-quant : exclude i32 ffn_gate_tid2eid routing table from quantization (#25787) DeepSeek-V4's ffn_gate_tid2eid tensor is an i32 token-id -> expert-id index table, not weights. It was never…