github
GitHub APIExtracts: 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
# PyTorch 2.13.0 Release Notes - [Highlights](#highlights) - [Backwards Incompatible Changes](#backwards-incompatible-changes) - [Deprecations](#deprecations) - [New Features](#new-features) - [Improvements](#improvements) - [Bug fixes](#bug-fixes) - [Performance](#perfo
github:pytorch/pytorch- 2026-07-08ggerganov/llama.cpp b9912: b9912
<details open> spec : fix naming, spacing (#25410) </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9912/llama-b9912-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://git
github:ggerganov/llama.cpp - 2026-07-08ggerganov/llama.cpp b9911: b9911
<details open> CUDA: Fuse MMVQ post-scale for NVFP4 (#24481) * CUDA: Fuse MMVQ for NVFP4 and BS 1 TODO: 1. Add tests to test-backend-ops (did verify correctness manually for one model) 2. Reorder bias/scale once PRs for NVFP4 are merged/landed * Add dense MMVQ fusion as we
github:ggerganov/llama.cpp - 2026-07-08ggerganov/llama.cpp b9910: b9910
<details open> server : fix draft model fit vs load inconsistency (#25056) * fix: draft model fit vs load inconsistency * refactor(server): unify draft/mtp parameter initialization, model, and context load - moves speculative init to speculative.cpp - changes server_context_im
github:ggerganov/llama.cpp - 2026-07-08NVIDIA/cutlass v4.5.3: CUTLASS 4.5.3
### CuTe DSL * Bug fixing and improvements - Fixed a compilation time regression issue in 4.5.0. Compilation times now match those in the 4.4 and 4.6 branches.
NVDAgithub:NVIDIA/cutlass - 2026-07-08ggerganov/llama.cpp b9909: b9909
<details open> server : add timings and progress to /responses API stream (#25348) </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9909/llama-b9909-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI
github:ggerganov/llama.cpp - 2026-07-08ggerganov/llama.cpp b9908: b9908
<details open> server: enforce prompt cache RAM limit (#25070) Before this commit, --cache-ram was not a hard limit: - The cache always kept at least one entry, even if that entry exceeded the RAM/token limits. - Old entries were only evicted for the RAM/token limits after s
github:ggerganov/llama.cpp - 2026-07-08ggerganov/llama.cpp b9907: b9907
<details open> common : add missing <fstream> include in common.h (#25220) Signed-off-by: zhangrunda <zhangrunda1234@outlook.com> </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9907/llama-b9907-bin-macos-arm6
github:ggerganov/llama.cpp - 2026-07-08ggerganov/llama.cpp b9906: b9906
<details open> ggml-hip : add -fno-finite-math-only alongside -ffast-math (#25373) -ffast-math implies -ffinite-math-only under ROCm/clang 22, which disables INFINITY/NaN and triggers -Wnan-infinity-disabled (errors under -Werror in CI). Re-enable infinity handling without drop
github:ggerganov/llama.cpp - 2026-07-08ggerganov/llama.cpp b9905: b9905
<details open> llama: fix quantized kv-cache for dsv4 (#25202) </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9905/llama-b9905-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED]
github:ggerganov/llama.cpp - 2026-07-07ggerganov/llama.cpp b9904: b9904
<details open> [SYCL] fix unsupported UT cases of CONT & CPY (#25231) * fix unsupported UT cases of CONT & CPY * update ops.md * rm unused head file </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9904/llama
github:ggerganov/llama.cpp