github
GitHub APIKeeps: repo, release, stars delta
- 2026-05-26ggerganov/llama.cpp b9352: b9352
<details open> ggml-zendnn : fixed naming of matmul function (#20964) * ggml-zendnn: fixed naming of matmul function * ggml-zendnn: fixed naming of mul_mat_id function * ggml-zendnn: fixed print in mul_mat_id --------- Co-authored-by: plotnikov.v10 <plotnikov.v10@wb.ru> <
AAPLgithub:ggerganov/llama.cpp - 2026-05-26ggerganov/llama.cpp b9351: b9351
<details open> </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9351/llama-b9351-bin-macos-arm64.tar.gz) - [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releases/download
AAPLgithub:ggerganov/llama.cpp - 2026-05-26ggerganov/llama.cpp b9334: b9334
<details open> CUDA: missing PDL sync for FWHT, better fallback (#23690) </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9334/llama-b9334-bin-macos-arm64.tar.gz) - [macOS Apple Silicon (arm64, KleidiAI enabled)
AAPLgithub:ggerganov/llama.cpp - 2026-05-26ggerganov/llama.cpp b9333: b9333
<details open> metal : add apple device id (#23566) Co-authored-by: lvyichen <lvyichen@stepfun.com> </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9333/llama-b9333-bin-macos-arm64.tar.gz) - [macOS Apple Silic
AAPLgithub:ggerganov/llama.cpp - 2026-05-26ggerganov/llama.cpp b9331: b9331
<details open> ci : reduce PR jobs by matching backend paths (#23675) * ci : disable SYCL f16 builds * ci : extract android and hip into separate workflows * ci : move webgpu to separate workflow * ci : move the rpc to a separate workflow * ci : extract s309x and ppcl jobs
AAPLgithub:ggerganov/llama.cpp - 2026-05-26ggerganov/llama.cpp b9330: b9330
<details open> model: tag ffn_latent as MUL_MAT to fix buft probe (#23664) ffn_latent_down/up are declared GGML_OP_MUL in LLM_TENSOR_INFOS but nemotron-h feeds them through ggml_mul_mat. The loader buft probe asks the backend about the declared op, so it tested an elementwise M
AAPLgithub:ggerganov/llama.cpp - 2026-05-26ggerganov/llama.cpp b9329: b9329
<details open> CUDA: add fast walsh-hadamard transform (#23615) * CUDA: add fast walsh-hadamard transform * review: add unrolls + change size_t -> int * warp size 64 --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de> </details> **macOS/iOS:** - [macOS Apple Sili
AAPLgithub:ggerganov/llama.cpp - 2026-05-26ggerganov/llama.cpp b9326: b9326
<details open> sync : ggml </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9326/llama-b9326-bin-macos-arm64.tar.gz) - [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releas
AAPLgithub:ggerganov/llama.cpp