github

GitHub API

8 events on 2026-08-02role: 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: 2026-08-25 · run status: success with data

← prev day2026-08-02next day →all history

2026-08-02ggerganov/llama.cpp b10235: b10235
<details open> metal : add SILU_BACK (#25982) * feat(silu_back): implemented silu_back op for f32 * fix(silu_back): removed redundant asserts in ggml-metal-ops.cpp function ggml_metal_op_silu_back. </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple
github:ggerganov/llama.cpp
2026-08-02ggerganov/llama.cpp b10234: b10234
<details open> metal : add F16 support for bin ops (#26465) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10234/llama-b10234-bin-macos-arm64.tar.gz) - macOS Apple Silicon (
github:ggerganov/llama.cpp
2026-08-02ggerganov/llama.cpp b10233: b10233
<details open> opencl: limit local workgroup size for GLU operation (#26383) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10233/llama-b10233-bin-macos-arm64.tar.gz) - macO
github:ggerganov/llama.cpp
2026-08-02ggerganov/llama.cpp b10232: b10232
<details open> metal: implement DeepSeek V4 hyper-connections (#26459) - Implement GGML_OP_DSV4_HC_COMB, GGML_OP_DSV4_HC_PRE, and GGML_OP_DSV4_HC_POST with SIMDgroup register and shuffle optimized kernels. - Add Metal dispatch and support plumbing and test the production Sink
github:ggerganov/llama.cpp
2026-08-02ggerganov/llama.cpp b10231: b10231
<details open> common: support the DSpark sidecar resolution (#26458) The dspark- files resolve like the other speculative sidecars: the -hfd tag applies to them, a requested sidecar resolves without a full model at the tag, and an explicit -md selection disables the discovery.
github:ggerganov/llama.cpp
2026-08-02ggerganov/llama.cpp b10229: b10229
<details open> opencl: bugfix increment ref_count in ggml_backend_opencl_init() (#26162) Incrementing `ref_count` at the beginning is important later in the `free()` method of the `ggml_backend_opencl_context` at program end. If we do not increment the `ref_count`, the result
github:ggerganov/llama.cpp
2026-08-02ggerganov/llama.cpp b10228: b10228
<details open> DeepseekV4 MTP + DSpark (#25784) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10228/llama-b10228-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, Kleid
github:ggerganov/llama.cpp
2026-08-02ggerganov/llama.cpp b10224: b10224
<details open> ggml-webgpu: add support for f16 repeat (#26307) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10224/llama-b10224-bin-macos-arm64.tar.gz) - macOS Apple Silic
github:ggerganov/llama.cpp