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: 2026-08-25 · run status: success with data
- 2026-07-18ggerganov/llama.cpp b10068: b10068
<details open> 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 trailing whitespace ---------
github:ggerganov/llama.cpp - 2026-07-18ggerganov/llama.cpp b10067: b10067
<details open> 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 added to the name-based exclusion list alongside ffn_gate_inp.weight,
github:ggerganov/llama.cpp