shipfeedAI news, curated daily

00:49:37 CET
12 OCT00:49:37shipfeed⋯
pull to refreshlast sync
Just in — 30 new
§ tools · storyline

Turns GGML_RPC_DEBUG into a verbosity level (0-3)

GGML RPC backend turns GGML_RPC_DEBUG into a verbosity level (0-3) with unified logging infrastructure.

yesterday · · primary fetch1 sourceupdated yesterday ·

rpc : turn GGML_RPC_DEBUG into a verbosity level and add logs (#29544) rpc : turn GGML_RPC_DEBUG into a verbosity level and add logs GGML_RPC_DEBUG is now parsed as a number: 0/unset disables debug logs, 1-3 emit increasingly detailed output (events, per-command trace, transport detail). Non-numeric values fall back to 1. The duplicated env/macro blocks in ggml-rpc.cpp and transport.cpp are replaced by a shared log.h, which becomes the single choke point for all logging of the RPC backend: LOG_ERROR/LOG_WARN/LOG_INFO for unconditional severity logs and LOG_DBG/LOG_DBG2/LOG_DBG3 for the verbosity-gated ones.

The transport files no longer need ggml-impl.h, and the server banner now also goes through the ggml logger (stderr). Missing logs are added on both the client (handshake, buffer ops, tensor transfers, graph computes, cache decisions) and the server (per-command dispatch, graph nodes), including the negotiated transport via the new socket_t::transport_name(). Assisted-by: pi:llama.cpp/MiMo-V2.6-Flash-RL rpc : align log levels with the documented verbosity semantics The first pass introduced GGML_RPC_DEBUG levels, but many call sites did not follow the documented semantics and…

read full article on github.com ↗
§ sources1 publication · timeline below
  1. github.comllama.cpp b11557primary