From ec933b837d0f999a207cd659cb839d6b237a37ac Mon Sep 17 00:00:00 2001 From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com> Date: Fri, 17 Jul 2026 12:47:13 +0200 Subject: [PATCH] chore(moss-transcribe-cpp): bump pin to CUDA K-quant embed fix (#10862) (#10878) chore(moss-transcribe-cpp): bump pin to CUDA K-quant embed fix Bumps the moss-transcribe.cpp pin to 190a569c, which merges the host-side embed-lookup fallback for K-quant token_embd tensors (localai-org/moss-transcribe.cpp#2). Before this, running a q5_K/q4_K/q6_K moss-transcribe GGUF on CUDA (or any non-CPU backend) aborted in getrows.cu with "unsupported src0 type: q5_K" because ggml's GET_ROWS op has no K-quant implementation on GPU, killing the backend process on the first request. The engine now dequantizes the needed rows on the host when the backend cannot run GET_ROWS for the tensor type, producing bit-identical results. Fixes #10862 Assisted-by: Claude:claude-opus-4-8 [Bash] [Edit] Signed-off-by: Ettore Di Giacinto Co-authored-by: Ettore Di Giacinto --- backend/go/moss-transcribe-cpp/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/backend/go/moss-transcribe-cpp/Makefile b/backend/go/moss-transcribe-cpp/Makefile index ad8f5a5ea..98f20ddb7 100644 --- a/backend/go/moss-transcribe-cpp/Makefile +++ b/backend/go/moss-transcribe-cpp/Makefile @@ -1,6 +1,6 @@ # moss-transcribe-cpp backend Makefile. # -# Upstream pin lives below as MOSS_VERSION?=92a923dca88a41a34e47a364d55ee25731a9a0a2 +# Upstream pin lives below as MOSS_VERSION?=190a569c13b4b247450f2fb3b2a431244e84833e # (.github/bump_deps.sh) can find and update it - matches the # whisper.cpp / parakeet-cpp / ds4 convention. # @@ -15,7 +15,7 @@ # That's what the L0 smoke test uses. The default target below does the proper # clone-at-pin + cmake build so CI doesn't need a side-checkout. -MOSS_VERSION?=92a923dca88a41a34e47a364d55ee25731a9a0a2 +MOSS_VERSION?=190a569c13b4b247450f2fb3b2a431244e84833e MOSS_REPO?=https://github.com/mudler/moss-transcribe.cpp GOCMD?=go