diff --git a/backend/cpp/turboquant/Makefile b/backend/cpp/turboquant/Makefile
index cdfb0489f..062ccda2d 100644
--- a/backend/cpp/turboquant/Makefile
+++ b/backend/cpp/turboquant/Makefile
@@ -1,7 +1,7 @@
 
 # Pinned to the HEAD of feature/turboquant-kv-cache on https://github.com/TheTom/llama-cpp-turboquant.
 # Auto-bumped nightly by .github/workflows/bump_deps.yaml.
-TURBOQUANT_VERSION?=2cbfdc62a1a047b01377948dfdede8cb6a744866
+TURBOQUANT_VERSION?=4c1c3ac09d2dba0aa9a55b94f6c50c41a92f9c8c
 LLAMA_REPO?=https://github.com/TheTom/llama-cpp-turboquant
 
 CMAKE_ARGS?=
diff --git a/backend/cpp/turboquant/patch-grpc-server.sh b/backend/cpp/turboquant/patch-grpc-server.sh
index c9555052e..3a61e21c4 100755
--- a/backend/cpp/turboquant/patch-grpc-server.sh
+++ b/backend/cpp/turboquant/patch-grpc-server.sh
@@ -9,7 +9,7 @@
 # fork and upstream (flat vs nested `common_params_speculative`, missing
 # `get_media_marker()`, `ctx_server.impl->model` vs `model_tgt`, and a
 # LOCALAI_LEGACY_LLAMA_CPP_SPEC compile gate). As of TURBOQUANT_VERSION
-# 2cbfdc62 the fork has rebased past ggml-org/llama.cpp#21962, #22397 and
+# 4c1c3ac0 the fork has rebased past ggml-org/llama.cpp#21962, #22397 and
 # #22838, so the shared grpc-server.cpp compiles unmodified against the fork.
 # Only the fork-specific KV-cache enum entries remain.
 #