github

GitHub API

6 events on 2026-07-07role: entity7d fetch windowcadence: dailyaccess: keyless

Extracts: repo, release, stars delta · metadata or bounded excerpt

Retention: D1 event history with canonical source link and deduplication metadata.

Access basis: Public API; token recommended for production rate limits.

Last ingested: 2026-08-26 · run status: success with data

← prev day2026-07-07next day →all history

2026-07-07ggerganov/llama.cpp b9902: b9902
<details open> [SYCL] support OP cross_entropy_loss, cross_entropy_loss_back (#25236) * support OP cross_entropy_loss, cross_entropy_loss_back * correct format issue </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/down
github:ggerganov/llama.cpp
2026-07-07ggerganov/llama.cpp b9894: b9894
<details open> vulkan : check src0 type in GGML_OP_SET_ROWS to avoid failures due to unimplemented f16 support (#25351) * vulkan : check src0 type in GGML_OP_SET_ROWS to avoid failures due to unimplemented f16 support * chore : get rid of else --------- Co-authored-by: Stani
github:ggerganov/llama.cpp
2026-07-07ggerganov/llama.cpp b9893: b9893
<details open> opencl: general flash attention decode performance optimizations (#25366) * opencl: vec flash-attention decode kernels for f16/q8_0/q4_0 KV * opencl: improve non FA KQ mv kernels * opencl: tweaks for multiquery FA * opencl: some tweaks for FA q1 kernels * ope
github:ggerganov/llama.cpp
2026-07-06ggerganov/llama.cpp b9892: b9892
<details open> common: Set optimal default thread count for ppc ( linux as well as AIX) (#25237) </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9892/llama-b9892-bin-macos-arm64.tar.gz) - macOS Apple Silicon (a
github:ggerganov/llama.cpp
2026-07-06ggerganov/llama.cpp b9891: b9891
<details open> metal: add col2im_1d op (f32/f16/bf16) (#25176) * metal: add col2im_1d op (f32/f16/bf16) Gather kernel mirroring the CPU/CUDA path: each output (t_out, oc) reads its ceil(K/s0) source columns with an F32 accumulator, a single write and no atomics. One thread per
github:ggerganov/llama.cpp
2026-07-06ggerganov/llama.cpp b9890: b9890
<details open> CUDA: remove -sm row, refactor cuBLAS (#24216) * CUDA: remove -sm row, refactor cuBLAS * fix CDNA + BF16 logic * fix bad return * fix src0 strides, contiguous requirements * fix GGML_CUDA_FORCE_CUBLAS * fix casts to BF16 </details> **macOS/iOS:** - [macOS
github:ggerganov/llama.cpp