gallery: add LFM2.5 2.6B variants (#11351)

Add LiquidAI official Q4_K_M and Q8_0 GGUF builds with linked variant selection and documented generation defaults.

Assisted-by: Codex:gpt-5 [Hugging Face]

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>

.docker/llama-cpp-build-target.sh

@@ -8,8 +8,15 @@ build_type=${2-}
 # ggml-cpu/arch/x86/repack.cpp at -march=sapphirerapids: the job sits on that one
 # translation unit until GitHub kills it at 6h. gcc builds the same file in
 # seconds, so only the SYCL images have to give up the CPU variant matrix.
+#
+# ROCm runs out of the same 6h budget for a different reason: volume, not a
+# stall. hipcc compiles ggml's HIP kernels once per entry in AMDGPU_TARGETS,
+# which is eleven architectures (gfx908 through gfx1201), and the CPU variant
+# matrix lands on top of that. The job built in 2h27m before it was added and
+# has been killed at exactly 6h00m on every run since, so no ROCm llama-cpp
+# image has been published since 2026-08-01.
 case "$build_type" in
-  sycl*)
+  sycl*|hipblas*)
     echo llama-cpp-fallback
     exit 0
     ;;

backend/cpp/audio-cpp/Makefile

@@ -9,7 +9,7 @@
 # recipe is a make target (not a prepare.sh) so 'make purge && make' is a clean
 # rebuild and so the bump bot can see the pin.
 
-AUDIO_CPP_VERSION?=5a8312ef7b8aa7cf14e9a24ac568cabd8725d68a
+AUDIO_CPP_VERSION?=238ab6a9e321c17de8e120559f57efeedaeb1345
 AUDIO_CPP_REPO?=https://github.com/0xShug0/audio.cpp
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))

backend/cpp/ds4/CMakeLists.txt

@@ -69,7 +69,15 @@ target_include_directories(hw_grpc_proto PUBLIC ${CMAKE_CURRENT_BINARY_DIR})
 
 set(DS4_OBJS "${DS4_DIR}/ds4.o")
 if(DS4_GPU STREQUAL "cuda")
-    list(APPEND DS4_OBJS "${DS4_DIR}/ds4_cuda.o")
+    list(APPEND DS4_OBJS
+        "${DS4_DIR}/ds4_cuda.o"
+        "${DS4_DIR}/cuda/mmq/ds4_ggml_stubs.o"
+        "${DS4_DIR}/cuda/mmq/ds4_mmq.o"
+        "${DS4_DIR}/cuda/mmq/ds4_mmq_d2r.o"
+        "${DS4_DIR}/cuda/mmq/quantize.o"
+        "${DS4_DIR}/cuda/mmq/mmid.o"
+        "${DS4_DIR}/cuda/mmq/mmvq.o"
+        "${DS4_DIR}/cuda/mmq/ds4_repack.o")
 elseif(DS4_GPU STREQUAL "metal")
     list(APPEND DS4_OBJS "${DS4_DIR}/ds4_metal.o")
 elseif(DS4_GPU STREQUAL "cpu")

backend/cpp/ds4/Makefile

@@ -1,10 +1,10 @@
 # ds4 backend Makefile.
 #
-# Upstream pin lives below as DS4_VERSION?=54b36ed9ba42da31b24f2d1a5feb075c2475dbb1
+# Upstream pin lives below as DS4_VERSION?=6747e7718dd08f00b680d0c16231f2d59ec3747e
 # (.github/bump_deps.sh) can find and update it - matches the
 # llama-cpp / ik-llama-cpp / turboquant convention.
 
-DS4_VERSION?=54b36ed9ba42da31b24f2d1a5feb075c2475dbb1
+DS4_VERSION?=6747e7718dd08f00b680d0c16231f2d59ec3747e
 DS4_REPO?=https://github.com/antirez/ds4
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
@@ -23,7 +23,9 @@ CMAKE_ARGS ?= -DCMAKE_BUILD_TYPE=Release
 # are shared by every GPU mode, so append them unconditionally below.
 ifeq ($(BUILD_TYPE),cublas)
     CMAKE_ARGS += -DDS4_GPU=cuda
-    DS4_OBJ_TARGET := ds4.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
+    DS4_OBJ_TARGET := ds4.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o \
+        cuda/mmq/ds4_ggml_stubs.o cuda/mmq/ds4_mmq.o cuda/mmq/ds4_mmq_d2r.o \
+        cuda/mmq/quantize.o cuda/mmq/mmid.o cuda/mmq/mmvq.o cuda/mmq/ds4_repack.o
 else ifeq ($(UNAME_S),Darwin)
     CMAKE_ARGS += -DDS4_GPU=metal
     DS4_OBJ_TARGET := ds4.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
@@ -55,7 +57,7 @@ ds4:
 # the right per-platform compile flags (Objective-C/Metal on Darwin, nvcc on Linux+CUDA).
 ds4/ds4.o: ds4
 ifeq ($(BUILD_TYPE),cublas)
-	+$(MAKE) -C ds4 ds4.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
+	+$(MAKE) -C ds4 $(DS4_OBJ_TARGET)
 else ifeq ($(UNAME_S),Darwin)
 	+$(MAKE) -C ds4 ds4.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
 else

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=cb9147fd0d9c08a9a84eee5ac405a73f4e10e3e1
+IK_LLAMA_VERSION?=6b55d2c7504f482e7c8ec6cbf22a19f3778c522b
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/go/crispasr/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # CrispASR version (release tag)
 CRISPASR_REPO?=https://github.com/CrispStrobe/CrispASR
-CRISPASR_VERSION?=fcb79282a6bc52e13d858026c42b24fb6e63c97a
+CRISPASR_VERSION?=ec730908a418b6032f9e69ded6186d3f042a7747
 SO_TARGET?=libgocrispasr.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/go/stablediffusion-ggml/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=db99efdd6d2a43c7937fd55b3359206c680a75b0
+STABLEDIFFUSION_GGML_VERSION?=ea7f0c87cfe4c673263b4c201c596c7f1cbe2528
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 

backend/go/vllm-cpp/Makefile

@@ -11,7 +11,30 @@ JOBS?=$(shell nproc --ignore=1 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || e
 
 # vllm.cpp version
 VLLM_CPP_REPO?=https://github.com/mudler/vllm.cpp
-VLLM_CPP_VERSION?=9e1c9025ae61167a3335454d7cc0de6093c21845
+VLLM_CPP_VERSION?=0757cac231ecd571a83c4fd2f50805c9251fc225
+
+# MLX GEMM provider (darwin/metal only; see the metal branch below for why).
+# Consumed as the prebuilt pip wheel: building MLX from source needs `xcrun
+# metal`, i.e. a full Xcode the macOS runners do not have, while the wheel ships
+# include/, lib/libmlx.dylib and the compiled mlx.metallib ready to link.
+#
+# DEFAULT ON, but ONLY because VLLM_CPP_VERSION above is pinned at or past
+# vllm.cpp 89c46aeb, which SHAPE-GATES the provider to prefill. The ordering is
+# load-bearing, not incidental:
+#
+#   pin >= 89c46aeb, MLX on   -> 99.1% of MLX-LM  (gated: prefill only)
+#   pin <  89c46aeb, MLX on   -> ~51%             (ungated: it also takes decode)
+#
+# MLX's steel GEMM wins prefill (537 ms TTFT against 602) and loses decode badly,
+# because the provider pays an mx::eval sync plus an output memcpy per call and
+# decode makes ~112 calls per TOKEN. Ungated it does both; gated it does only the
+# good half. So if this pin is ever moved BACKWARDS, this default must go with it.
+VLLM_CPP_MLX?=on
+MLX_VERSION?=0.29.4
+MLX_VENV?=$(abspath ./mlx-venv)
+# Resolved lazily (recursive `=`, not `:=`): the glob only matches once the venv
+# target has run, and the interpreter version in the path varies per runner.
+MLX_ROOT=$(shell echo $(MLX_VENV)/lib/python*/site-packages/mlx)
 
 # The backend consumes only the stable C ABI (libvllm + include/vllm.h), so the
 # server, examples and tests of the engine are never built here.
@@ -49,6 +72,23 @@ else ifeq ($(BUILD_TYPE),vulkan)
 	CMAKE_ARGS+=-DVLLM_CPP_VULKAN=ON -DVLLM_CPP_CUDA=OFF
 else ifeq ($(BUILD_TYPE),metal)
 	CMAKE_ARGS+=-DVLLM_CPP_METAL=ON
+	# The optional MLX GEMM provider. vllm.cpp keeps it OFF by default because it
+	# is a ~19 MB libmlx.dylib plus a ~105 MB mlx.metallib, and upstream's
+	# position is that it must earn that cost by measurement. It does, on the
+	# only hardware this build targets: measured on an Apple M4 against the
+	# native MSL GEMM in the SAME binary (arms toggled by
+	# VT_OP_PROVIDER_DISABLE=mlx), Qwen3-1.7B-bf16 p=512 g=128, it is 1.5x to
+	# 2.2x aggregate throughput and 2x to 3x faster TTFT, at equal peak memory
+	# and bit-identical output on every parity shape. See vllm.cpp
+	# docs/BENCHMARKS.md "MLX GEMM provider A/B on Apple M4".
+	#
+	# MLX delegates the dense GEMM ONLY: kPagedAttention stays vllm.cpp's own
+	# kernel, because MLX has no paged-KV primitive at all.
+	#
+	# Set VLLM_CPP_MLX=off for a Metal build without it (smaller image, slower).
+	ifeq ($(VLLM_CPP_MLX),on)
+		MLX_ENABLED=1
+	endif
 else
 	CMAKE_ARGS+=-DVLLM_CPP_CUDA=OFF
 endif
@@ -68,10 +108,35 @@ sources/vllm.cpp:
 	git fetch --depth 1 origin $(VLLM_CPP_VERSION) && \
 	git checkout FETCH_HEAD
 
-$(LIB): sources/vllm.cpp
+ifeq ($(MLX_ENABLED),1)
+# A stamp FILE, not a phony target: a phony prerequisite is always "newer" than
+# $(LIB) and would re-link libvllm on every invocation. Keyed on the version so
+# a MLX_VERSION bump reinstalls instead of silently reusing the old wheel.
+MLX_STAMP=$(MLX_VENV)/.mlx-$(MLX_VERSION).stamp
+MLX_CMAKE_ARGS=-DVLLM_CPP_MLX=ON -DMLX_ROOT=$(MLX_ROOT)
+
+$(MLX_STAMP):
+	@if [ ! -x "$(MLX_VENV)/bin/pip" ]; then \
+		python3 -m venv "$(MLX_VENV)" || { echo "vllm-cpp: python3 with venv is required to build the MLX provider; pass VLLM_CPP_MLX=off to build Metal without it" >&2; exit 1; }; \
+	fi
+	"$(MLX_VENV)"/bin/pip install --quiet --disable-pip-version-check "mlx==$(MLX_VERSION)"
+	@# Resolved in the SHELL, not by $(MLX_ROOT): make expands a whole recipe
+	@# before running its first line, so the glob would still be unmatched here.
+	@# Every later use (the cmake args, package.sh) expands after this target has
+	@# completed, where $(MLX_ROOT) does resolve.
+	@root=$$(echo "$(MLX_VENV)"/lib/python*/site-packages/mlx); \
+	test -f "$$root/lib/libmlx.dylib" -a -f "$$root/include/mlx/array.h" || \
+		{ echo "vllm-cpp: mlx==$(MLX_VERSION) did not provide lib/libmlx.dylib + include/mlx/array.h under $$root" >&2; exit 1; }
+	touch $@
+else
+MLX_STAMP=
+MLX_CMAKE_ARGS=
+endif
+
+$(LIB): sources/vllm.cpp $(MLX_STAMP)
 	mkdir -p build && \
 	cd build && \
-	cmake ../sources/vllm.cpp $(CMAKE_ARGS) && \
+	cmake ../sources/vllm.cpp $(CMAKE_ARGS) $(MLX_CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target vllm_shared
 	cp -fL build/$(LIB) ./$(LIB)
 
@@ -79,12 +144,12 @@ vllm-cpp: main.go govllmcpp.go backend.go options.go $(LIB)
 	CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o vllm-cpp ./
 
 package: vllm-cpp
-	bash package.sh
+	MLX_ROOT="$(MLX_ROOT)" bash package.sh
 
 build: package
 
 clean: purge
-	rm -rf libvllm.so libvllm.dylib package sources/vllm.cpp vllm-cpp
+	rm -rf libvllm.so libvllm.dylib package sources/vllm.cpp vllm-cpp "$(MLX_VENV)"
 
 purge:
 	rm -rf build

backend/go/vllm-cpp/README.md

@@ -41,5 +41,50 @@ options:
 - max_num_seqs:16
 ```
 
+## Apple Silicon: the MLX GEMM provider (ON by default, gated to prefill)
+
+`BUILD_TYPE=metal` builds vllm.cpp's MLX provider for the dense GEMM
+(`VLLM_CPP_MLX=on`, the default here). It is on because upstream now SHAPE-GATES
+it to prefill; it was briefly off in this branch's history, and that was correct
+at the time for an ungated provider.
+
+The gate matters more than the flag. MLX's steel GEMM wins prefill but loses
+decode, because the provider pays an `mx::eval` synchronisation plus an output
+memcpy on every call and decode makes ~112 calls *per token*. Measured on an
+Apple M4, Qwen3-1.7B-bf16 warm at p=512 g=128:
+
+| configuration | prefill TTFT | warm throughput |
+|---|--:|--:|
+| MLX **gated to prefill** (pin >= 89c46aeb) | **524.5 ms** | **24.37 tok/s, 97.6% of MLX-LM** |
+| MLX ungated (older pins) | 537 ms | 12.7 tok/s |
+| MLX off | 602 ms | 23.9 tok/s, 95.9% |
+
+Ratios are against an MLX-LM baseline measured INTERLEAVED with ours over four
+ABBA blocks (its spread 0.34%, ours 0.12%). An earlier revision of this file
+claimed 99.1%; that used a two-run MLX-LM baseline containing an outlier and
+overstated us by about 1.5 points.
+
+**`VLLM_CPP_VERSION` and this flag are coupled.** Moving the pin back before
+`89c46aeb` while leaving `VLLM_CPP_MLX=on` would take the middle row — roughly
+half throughput. If you roll the pin back, roll the default back with it.
+
+One caveat: MLX's GEMM is not bit-identical to the native kernel, so an MLX build
+produces a different greedy sequence than a non-MLX one. That is a property of the
+provider, not of the gate, and it predates this packaging. Full disposition in
+vllm.cpp `docs/BENCHMARKS.md`.
+
+Build knobs:
+
+- `VLLM_CPP_MLX=off` builds Metal without the provider: ~124 MB smaller, and
+  96.4% of MLX-LM instead of 99.1%.
+- `MLX_VERSION` pins the wheel (default `0.29.4`). MLX is consumed as the
+  prebuilt pip wheel because building it from source needs `xcrun metal`, i.e. a
+  full Xcode the macOS runners do not have.
+
+Packaging vendors `libmlx.dylib`, `mlx.metallib` and MLX's MIT license into
+`package/lib/`, and rewrites `libvllm.dylib`'s rpath to `@loader_path/lib`
+(re-signing it, since `install_name_tool` invalidates the signature). The
+metallib must stay beside `libmlx.dylib`: MLX looks for it there.
+
 Testing: `make test` runs the unit specs; export `VLLM_CPP_MODEL=<model>` (and
 optionally `VLLM_CPP_LIBRARY=<libvllm path>`) to enable the e2e specs.

backend/go/vllm-cpp/package.sh

@@ -43,6 +43,50 @@ elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
     cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
 elif [ $(uname -s) = "Darwin" ]; then
     echo "Detected Darwin"
+    # Vendor the optional MLX GEMM provider, when libvllm was built against it.
+    # Three facts drive every line below, each verified on an Apple M4 before it
+    # was written:
+    #   1. libvllm.dylib carries an LC_LOAD_DYLIB on @rpath/libmlx.dylib, and its
+    #      build-time LC_RPATH points inside the build venv. That path does not
+    #      exist on a user's machine, so it must become @loader_path/lib.
+    #   2. MLX finds its ~100 MB mlx.metallib beside its OWN dylib, so the two
+    #      files have to land in the same directory or every Metal op dies with
+    #      "Failed to load the default metallib".
+    #   3. install_name_tool invalidates the code signature, and macOS refuses to
+    #      load an arm64 image whose signature does not match, so the patched
+    #      library must be re-signed ad-hoc afterwards.
+    if otool -L "$CURDIR/package/libvllm.dylib" 2>/dev/null | grep -q "libmlx.dylib"; then
+        MLX_LIB_DIR="${MLX_ROOT}/lib"
+        if [ ! -f "$MLX_LIB_DIR/libmlx.dylib" ] || [ ! -f "$MLX_LIB_DIR/mlx.metallib" ]; then
+            echo "Error: libvllm.dylib links libmlx.dylib but $MLX_LIB_DIR is missing libmlx.dylib/mlx.metallib" >&2
+            exit 1
+        fi
+        echo "Vendoring the MLX GEMM provider from $MLX_LIB_DIR"
+        cp -fLv "$MLX_LIB_DIR/libmlx.dylib" "$CURDIR/package/lib/"
+        cp -fLv "$MLX_LIB_DIR/mlx.metallib" "$CURDIR/package/lib/"
+        # MLX is MIT and we redistribute its binaries, so its license ships with
+        # them. mlx-metal is the wheel carrying the dylib and the metallib.
+        MLX_LICENSE=$(ls "${MLX_ROOT}"/../mlx_metal-*.dist-info/licenses/LICENSE 2>/dev/null | head -1)
+        if [ -z "$MLX_LICENSE" ]; then
+            MLX_LICENSE=$(ls "${MLX_ROOT}"/../mlx-*.dist-info/licenses/LICENSE 2>/dev/null | head -1)
+        fi
+        if [ -z "$MLX_LICENSE" ]; then
+            echo "Error: could not find the MLX LICENSE to redistribute alongside libmlx.dylib" >&2
+            exit 1
+        fi
+        cp -fLv "$MLX_LICENSE" "$CURDIR/package/lib/LICENSE.mlx"
+        # Drop every build-tree rpath, then point at the packaged copy.
+        otool -l "$CURDIR/package/libvllm.dylib" | awk '/LC_RPATH/{f=1;next} f&&/ path /{print $2;f=0}' | while read -r rp; do
+            install_name_tool -delete_rpath "$rp" "$CURDIR/package/libvllm.dylib" 2>/dev/null || true
+        done
+        install_name_tool -add_rpath "@loader_path/lib" "$CURDIR/package/libvllm.dylib"
+        codesign -f -s - "$CURDIR/package/libvllm.dylib"
+        # A broken rpath must fail the BUILD, not the user's first inference.
+        if ! otool -l "$CURDIR/package/libvllm.dylib" | grep -q "@loader_path/lib"; then
+            echo "Error: libvllm.dylib did not get the @loader_path/lib rpath" >&2
+            exit 1
+        fi
+    fi
 else
     echo "Error: Could not detect architecture"
     exit 1

backend/go/whisper/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
-WHISPER_CPP_VERSION?=2ca53bb45e38748d07b310eeb36245a7157ac882
+WHISPER_CPP_VERSION?=306c88f4d1286aec1bf96e544632897886af5501
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/index.yaml

@@ -193,12 +193,22 @@
   alias: "vllm-cpp"
   license: apache-2.0
   description: |
-    vllm.cpp is a from-scratch C++20 port of vLLM created and maintained by the LocalAI team.
-    It mirrors vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching,
-    scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at
-    inference time. It loads Hugging Face safetensors and GGUF checkpoints, supports
-    structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine,
-    and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan.
+    ALPHA development builds. Try it, but llama-cpp stays the recommendation for
+    production use.
+
+    vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team,
+    developed in its own repository and usable without LocalAI. It began as a port of
+    vLLM and keeps vLLM as its reference implementation, checking output against it and
+    benchmarking against it, while growing a featureset of its own. It implements vLLM's
+    V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler,
+    sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference
+    time. It loads GGUF as well as Hugging Face safetensors, supports structured output
+    (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative
+    decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple
+    Metal and Vulkan.
+
+    The project is expected to be renamed as it diverges further from vLLM; the new
+    name is still to be decided.
   urls:
     - https://github.com/mudler/vllm.cpp
   tags:

core/http/react-ui/package-lock.json

@@ -21,9 +21,10 @@
         "@fortawesome/fontawesome-free": "^6.7.2",
         "@lezer/highlight": "^1.2.1",
         "@modelcontextprotocol/ext-apps": "^1.2.2",
-        "@modelcontextprotocol/sdk": "^1.25.1",
+        "@modelcontextprotocol/sdk": "^1.30.0",
         "dompurify": "^3.4.12",
         "highlight.js": "^11.11.1",
+        "hono": "4.12.34",
         "i18next": "^26.0.8",
         "i18next-browser-languagedetector": "^8.2.1",
         "i18next-http-backend": "^3.0.6",
@@ -635,12 +636,12 @@
       }
     },
     "node_modules/@hono/node-server": {
-      "version": "1.19.14",
-      "resolved": "https://registry.npmjs.org/@hono/node-server/-/node-server-1.19.14.tgz",
-      "integrity": "sha512-GwtvgtXxnWsucXvbQXkRgqksiH2Qed37H9xHZocE5sA3N8O8O8/8FA3uclQXxXVzc9XBZuEOMK7+r02FmSpHtw==",
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/@hono/node-server/-/node-server-2.1.0.tgz",
+      "integrity": "sha512-XovyyCCnBzW+zKu+z/zq8hwNs4KOR5rEMAOxo2f40Q5xoOI37IMm6MIg2COOUtUApo0i6850MTBKH2u4QLGIqg==",
       "license": "MIT",
       "engines": {
-        "node": ">=18.14.1"
+        "node": ">=20"
       },
       "peerDependencies": {
         "hono": "^4"
@@ -944,11 +945,12 @@
       }
     },
     "node_modules/@modelcontextprotocol/sdk": {
-      "version": "1.27.1",
-      "resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.27.1.tgz",
-      "integrity": "sha512-sr6GbP+4edBwFndLbM60gf07z0FQ79gaExpnsjMGePXqFcSSb7t6iscpjk9DhFhwd+mTEQrzNafGP8/iGGFYaA==",
+      "version": "1.30.0",
+      "resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.30.0.tgz",
+      "integrity": "sha512-xKd8OIzlqNzcqcNumGAa6g+PW2kjD5vrpcKOnfldAUPP3j7lnqMPwlTXQm8gF+UwH72z0lqaRbjr9hqGz0eITA==",
+      "license": "MIT",
       "dependencies": {
-        "@hono/node-server": "^1.19.9",
+        "@hono/node-server": "^1.19.9 || ^2.0.5",
         "ajv": "^8.17.1",
         "ajv-formats": "^3.0.1",
         "content-type": "^1.0.5",
@@ -1718,10 +1720,11 @@
       "dev": true
     },
     "node_modules/brace-expansion": {
-      "version": "1.1.12",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
-      "integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
+      "version": "1.1.18",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.18.tgz",
+      "integrity": "sha512-Edep/X9fGqVNmzKBVsDYIOtD+z1tuezV70LBjdCst9Tqu76lsnvRiZ6oTic1n+/BIwX6QDGAO94PN4N2SADvtw==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0",
         "concat-map": "0.0.1"
@@ -2876,9 +2879,9 @@
       "dev": true
     },
     "node_modules/fast-uri": {
-      "version": "3.1.4",
-      "resolved": "https://registry.npmjs.org/fast-uri/-/fast-uri-3.1.4.tgz",
-      "integrity": "sha512-8JnbkQ4juDyvYs4mgFGQqg4yCYtFDtUtmp2QIQq11ZZe5CFQ5wcqm1rqDgAh/QdMySuBnPzMUiJUNZG5N/AiQw==",
+      "version": "3.1.5",
+      "resolved": "https://registry.npmjs.org/fast-uri/-/fast-uri-3.1.5.tgz",
+      "integrity": "sha512-gHwA1O9LDIcKunMKhObS/HimwtehO1nPUECKAu5TpKgaO19fcWEl4bliWe1jWxVFvIXztJjjQ4L8XQ1EU9f7Jw==",
       "funding": [
         {
           "type": "github",
@@ -3432,9 +3435,9 @@
       }
     },
     "node_modules/hono": {
-      "version": "4.12.31",
-      "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.31.tgz",
-      "integrity": "sha512-zJIHFrl6bq3RDd2YusFNCDlM8qUprxKswyi/OPzPyzKDdyBXDqWx8bZlZ7R+saTdSTatUmb3O7K4SspGPaEOQg==",
+      "version": "4.12.34",
+      "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.34.tgz",
+      "integrity": "sha512-GqXJqY/xJkJmuloTrnV1ZEXG3fqte+VjkUqoRNZXcrUidiUOP4fMSIHHY4tsqZBK++kVyWmt/AAfSUuy57/eSA==",
       "license": "MIT",
       "engines": {
         "node": ">=16.9.0"
@@ -4193,9 +4196,9 @@
       "integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="
     },
     "node_modules/ip-address": {
-      "version": "10.2.0",
-      "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.2.0.tgz",
-      "integrity": "sha512-/+S6j4E9AHvW9SWMSEY9Xfy66O5PWvVEJ08O0y5JGyEKQpojb0K0GKpz/v5HJ/G0vi3D2sjGK78119oXZeE0qA==",
+      "version": "10.4.0",
+      "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.4.0.tgz",
+      "integrity": "sha512-oSK96Grm3aP6OrS263xVxbNDGVL7rzBtYdpGqlDG8iQdoenDoTs/nkki+DflYbAEE8Xl6o5YxhxlrKvI3nqKXQ==",
       "license": "MIT",
       "engines": {
         "node": ">= 12"
@@ -4383,16 +4386,16 @@
       }
     },
     "node_modules/istanbul-lib-processinfo/node_modules/brace-expansion": {
-      "version": "5.0.6",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.6.tgz",
-      "integrity": "sha512-kLpxurY4Z4r9sgMsyG0Z9uzsBlgiU/EFKhj/h91/8yHu0edo7XuixOIH3VcJ8kkxs6/jPzoI6U9Vj3WqbMQ94g==",
+      "version": "5.0.9",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.9.tgz",
+      "integrity": "sha512-ScQ4IuvIEF1TMlP7Zt+vjJ//9zlPb2SDcxWxM3bk8s6t6GGdJ7KO1dCcTidOPJKePW30LE/2cT7wCyPho9/Wxg==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "balanced-match": "^4.0.2"
       },
       "engines": {
-        "node": "18 || 20 || >=22"
+        "node": "20 || >=22"
       }
     },
     "node_modules/istanbul-lib-processinfo/node_modules/glob": {
@@ -5278,16 +5281,16 @@
       }
     },
     "node_modules/nyc/node_modules/brace-expansion": {
-      "version": "5.0.6",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.6.tgz",
-      "integrity": "sha512-kLpxurY4Z4r9sgMsyG0Z9uzsBlgiU/EFKhj/h91/8yHu0edo7XuixOIH3VcJ8kkxs6/jPzoI6U9Vj3WqbMQ94g==",
+      "version": "5.0.9",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.9.tgz",
+      "integrity": "sha512-ScQ4IuvIEF1TMlP7Zt+vjJ//9zlPb2SDcxWxM3bk8s6t6GGdJ7KO1dCcTidOPJKePW30LE/2cT7wCyPho9/Wxg==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "balanced-match": "^4.0.2"
       },
       "engines": {
-        "node": "18 || 20 || >=22"
+        "node": "20 || >=22"
       }
     },
     "node_modules/nyc/node_modules/convert-source-map": {
@@ -5974,10 +5977,11 @@
       }
     },
     "node_modules/quick-temp/node_modules/brace-expansion": {
-      "version": "2.1.0",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.0.tgz",
-      "integrity": "sha512-TN1kCZAgdgweJhWWpgKYrQaMNHcDULHkWwQIspdtjV4Y5aurRdZpjAqn6yX3FPqTA9ngHCc4hJxMAMgGfve85w==",
+      "version": "2.1.4",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.4.tgz",
+      "integrity": "sha512-hGfVzPxthbf3+2yjg/RBs60cB0FhqBS/zvdV/4wn4/BmN0bNMMHPc4V/BbFieqf1TKAGGAHnY4eSjajCl0f2Xg==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0"
       }
@@ -6569,16 +6573,16 @@
       }
     },
     "node_modules/spawn-wrap/node_modules/brace-expansion": {
-      "version": "5.0.6",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.6.tgz",
-      "integrity": "sha512-kLpxurY4Z4r9sgMsyG0Z9uzsBlgiU/EFKhj/h91/8yHu0edo7XuixOIH3VcJ8kkxs6/jPzoI6U9Vj3WqbMQ94g==",
+      "version": "5.0.9",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.9.tgz",
+      "integrity": "sha512-ScQ4IuvIEF1TMlP7Zt+vjJ//9zlPb2SDcxWxM3bk8s6t6GGdJ7KO1dCcTidOPJKePW30LE/2cT7wCyPho9/Wxg==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "balanced-match": "^4.0.2"
       },
       "engines": {
-        "node": "18 || 20 || >=22"
+        "node": "20 || >=22"
       }
     },
     "node_modules/spawn-wrap/node_modules/foreground-child": {
@@ -6902,16 +6906,16 @@
       }
     },
     "node_modules/test-exclude/node_modules/brace-expansion": {
-      "version": "5.0.6",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.6.tgz",
-      "integrity": "sha512-kLpxurY4Z4r9sgMsyG0Z9uzsBlgiU/EFKhj/h91/8yHu0edo7XuixOIH3VcJ8kkxs6/jPzoI6U9Vj3WqbMQ94g==",
+      "version": "5.0.9",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.9.tgz",
+      "integrity": "sha512-ScQ4IuvIEF1TMlP7Zt+vjJ//9zlPb2SDcxWxM3bk8s6t6GGdJ7KO1dCcTidOPJKePW30LE/2cT7wCyPho9/Wxg==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "balanced-match": "^4.0.2"
       },
       "engines": {
-        "node": "18 || 20 || >=22"
+        "node": "20 || >=22"
       }
     },
     "node_modules/test-exclude/node_modules/glob": {
@@ -7134,9 +7138,9 @@
       }
     },
     "node_modules/undici": {
-      "version": "7.28.0",
-      "resolved": "https://registry.npmjs.org/undici/-/undici-7.28.0.tgz",
-      "integrity": "sha512-cRZYrTDwWznlnRiPjggAGxZXanty6M8RV1ff8Wm4LWXBp7/IG8v5DnOm74DtUBp9OONpK75YlPnIjQqX0dBDtA==",
+      "version": "7.29.0",
+      "resolved": "https://registry.npmjs.org/undici/-/undici-7.29.0.tgz",
+      "integrity": "sha512-IDxfleLmmbSskfWSUATiN1nfn2rDuvnMOqb5CWR92iIfojA0Ud+ulOAAEQ57LPr9rWmsreUyf5lwyao+7GNNVw==",
       "dev": true,
       "license": "MIT",
       "engines": {

core/http/react-ui/package.json

@@ -19,7 +19,7 @@
     "coverage:report": "nyc report"
   },
   "overrides": {
-    "hono": "4.12.25"
+    "hono": "4.12.34"
   },
   "dependencies": {
     "@codemirror/autocomplete": "^6.18.6",
@@ -35,10 +35,10 @@
     "@fortawesome/fontawesome-free": "^6.7.2",
     "@lezer/highlight": "^1.2.1",
     "@modelcontextprotocol/ext-apps": "^1.2.2",
-    "@modelcontextprotocol/sdk": "^1.25.1",
+    "@modelcontextprotocol/sdk": "^1.30.0",
     "dompurify": "^3.4.12",
     "highlight.js": "^11.11.1",
-    "hono": "4.12.25",
+    "hono": "4.12.34",
     "i18next": "^26.0.8",
     "i18next-browser-languagedetector": "^8.2.1",
     "i18next-http-backend": "^3.0.6",

core/services/advisorylock/leader_loop_test.go

@@ -54,62 +54,57 @@ var _ = Describe("RunLeaderLoop", func() {
 				close(done)
 			}()
 
-			// Let it run a bit then cancel
-			time.Sleep(150 * time.Millisecond)
+			Eventually(func() int32 {
+				return atomic.LoadInt32(&callCount)
+			}, 500*time.Millisecond, 10*time.Millisecond).Should(BeNumerically(">=", 1))
 			cancel()
 
-			// RunLeaderLoop should return
 			Eventually(done, 500*time.Millisecond).Should(BeClosed())
-
-			// Record count after cancellation
-			countAfterCancel := atomic.LoadInt32(&callCount)
-			time.Sleep(150 * time.Millisecond)
-			countLater := atomic.LoadInt32(&callCount)
-
-			Expect(countLater).To(Equal(countAfterCancel),
-				"function should stop being called after context cancellation")
 		})
 
 		It("only one leader executes at a time (two concurrent loops)", func() {
 			db := testutil.SetupTestDB()
 			const lockKey int64 = 5002
 
-			var (
-				mu         sync.Mutex
-				maxRunning int32
-				running    int32
-			)
+			var running int32
+			entered := make(chan struct{}, 2)
+			release := make(chan struct{})
+			var releaseOnce sync.Once
 
 			ctx, cancel := context.WithCancel(context.Background())
-			defer cancel()
+			done := make(chan struct{}, 2)
+			DeferCleanup(func() {
+				cancel()
+				releaseOnce.Do(func() { close(release) })
+			})
 
 			fn := func() {
-				cur := atomic.AddInt32(&running, 1)
-				mu.Lock()
-				if cur > maxRunning {
-					maxRunning = cur
+				atomic.AddInt32(&running, 1)
+				select {
+				case entered <- struct{}{}:
+				default:
 				}
-				mu.Unlock()
-
-				time.Sleep(30 * time.Millisecond)
-
+				<-release
 				atomic.AddInt32(&running, -1)
 			}
 
-			// Start two competing leader loops with the same lock key
-			go RunLeaderLoop(ctx, db, lockKey, 50*time.Millisecond, fn)
-			go RunLeaderLoop(ctx, db, lockKey, 50*time.Millisecond, fn)
+			for range 2 {
+				go func() {
+					RunLeaderLoop(ctx, db, lockKey, 1*time.Millisecond, fn)
+					done <- struct{}{}
+				}()
+			}
+
+			Eventually(entered, 500*time.Millisecond).Should(Receive())
+			Consistently(func() int32 {
+				return atomic.LoadInt32(&running)
+			}, 50*time.Millisecond, 5*time.Millisecond).Should(Equal(int32(1)),
+				"expected only the lock holder to run while both loops tick")
 
-			// Let them run for a while
-			time.Sleep(400 * time.Millisecond)
 			cancel()
-
-			mu.Lock()
-			observed := maxRunning
-			mu.Unlock()
-
-			Expect(observed).To(BeNumerically("<=", 1),
-				"expected at most 1 goroutine running the leader function at a time")
+			releaseOnce.Do(func() { close(release) })
+			Eventually(done, 500*time.Millisecond).Should(Receive())
+			Eventually(done, 500*time.Millisecond).Should(Receive())
 		})
 	})
 })

gallery/index.yaml

@@ -785,35 +785,18 @@
 - name: "qwen3.6-35b-a3b-uncensored-genesis-hermes-v6"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
+    - https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
     - https://huggingface.co/LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-GGUF
   description: |
-    # Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
+    Qwen3.6-35B-A3B Uncensored Genesis Hermes V6 is LuffyTheFox's multimodal,
+    agentic derivative of HauhauCS's uncensored Qwen3.6-35B-A3B model. It
+    combines Genesis tensor calibration with Hermes function-calling data while
+    retaining the 35B mixture-of-experts architecture, roughly 3B active
+    parameters per token, and the native 262K-token context window.
 
-    > **Join the Discord** for updates, roadmaps, projects, or just to chat.
-
-    Qwen3.6-35B-A3B uncensored by HauhauCS. **0/465 Refusals.**
-
-    > **HuggingFace's "Hardware Compatibility" widget doesn't recognize K_P quants** — it may show fewer files than actually exist. Click **"View +X variants"** or go to **Files and versions** to see all available downloads.
-
-    ## About
-
-    No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.
-
-    These are meant to be the best lossless uncensored models out there.
-
-    ## Aggressive Variant
-
-    Stronger uncensoring — model is fully unlocked and won't refuse prompts. May occasionally append short disclaimers (baked into base model training, not refusals) but full content is always generated.
-
-    For a more conservative uncensor that keeps some safety guardrails, check the Balanced variant when it's available.
-
-    ## Downloads
-
-    All quants generated with importance matrix (imatrix) for optimal quality preservation on abliterated weights.
-
-    ## What are K_P quants?
-
-    ...
+    This entry installs the Q8_0 GGUF together with its F16 multimodal projector
+    for llama.cpp. The model card recommends Jinja chat templates and at least a
+    128K context for its thinking behavior. License: Apache-2.0.
   license: "apache-2.0"
   tags:
     - llm
@@ -2009,7 +1992,7 @@
   files:
     - filename: ds4flash.gguf
       uri: https://huggingface.co/unsloth/DeepSeek-V4-Flash-GGUF
-      sha256: 1bfdafd1c288eb1b2bcb629ee9e1b7567dcf0abbe4d20995905a3c3465e9bd1e
+      sha256: ba1d64ad8d77038124839956b614db2e889daa1a4ddc83060bb06ccb5a1d7461
 - name: "qwopus3.6-35b-a3b-coder-mtp"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
@@ -2631,6 +2614,83 @@
     - filename: llama-cpp/models/LFM2.5-1.2B-Instruct-GGUF/LFM2.5-1.2B-Instruct-Q4_K_M.gguf
       sha256: b1b3de114215d9507409a662a501a631095a479a419584e8a2ded6304b19b4f5
       uri: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct-GGUF/resolve/main/LFM2.5-1.2B-Instruct-Q4_K_M.gguf
+- &lfm2-5-2-6b
+  name: "lfm2.5-2.6b"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/LiquidAI/LFM2.5-2.6B
+    - https://huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF
+  description: |
+    LFM2.5-2.6B is LiquidAI's compact, text-only reasoning model for on-device
+    agentic workloads. It has 2.69B parameters, a 128K-token context window,
+    multilingual support, and post-training for tool use, instruction following,
+    data extraction, RAG, and multi-step agents. This entry uses the recommended
+    Q4_K_M GGUF quantization from LiquidAI's official repository.
+  license: "other"
+  tags:
+    - llm
+    - gguf
+    - reasoning
+    - cpu
+    - gpu
+  icon: https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png
+  variants:
+    - model: lfm2.5-2.6b-q8
+  overrides:
+    backend: llama-cpp
+    context_size: 131072
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - completion
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/LFM2.5-2.6B-GGUF/LFM2.5-2.6B-Q4_K_M.gguf
+      repeat_penalty: 1.1
+      temperature: 0.1
+      top_k: 50
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/LFM2.5-2.6B-GGUF/LFM2.5-2.6B-Q4_K_M.gguf
+      sha256: 79fdf00351b46cf26f020aead28d01889886be87c55fa0eb907e6f9b00bfee14
+      uri: https://huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF/resolve/main/LFM2.5-2.6B-Q4_K_M.gguf
+- !!merge <<: *lfm2-5-2-6b
+  name: "lfm2.5-2.6b-q8"
+  description: |
+    LFM2.5-2.6B is LiquidAI's compact, text-only reasoning model for on-device
+    agentic workloads. It has 2.69B parameters, a 128K-token context window,
+    multilingual support, and post-training for tool use, instruction following,
+    data extraction, RAG, and multi-step agents. This entry uses the higher-quality
+    Q8_0 GGUF quantization from LiquidAI's official repository.
+  variants: null
+  overrides:
+    backend: llama-cpp
+    context_size: 131072
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - completion
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/LFM2.5-2.6B-GGUF/LFM2.5-2.6B-Q8_0.gguf
+      repeat_penalty: 1.1
+      temperature: 0.1
+      top_k: 50
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/LFM2.5-2.6B-GGUF/LFM2.5-2.6B-Q8_0.gguf
+      sha256: 36587fdf27bdfc69caf2637273679a0870ec155162161bde6fd16e8c70bdb757
+      uri: https://huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF/resolve/main/LFM2.5-2.6B-Q8_0.gguf
 - name: "qwopus3.6-27b-coder-compat-mtp"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:

scripts/build/llama-cpp-build-target_test.sh

@@ -29,4 +29,11 @@ assert_target arm64 "" llama-cpp-cpu-all
 assert_target amd64 sycl_f16 llama-cpp-fallback
 assert_target amd64 sycl_f32 llama-cpp-fallback
 
+# ROCm exhausts the same 6h budget through volume rather than a stall: hipcc
+# compiles ggml's HIP kernels once per AMDGPU target, eleven of them, and the
+# CPU variant matrix goes on top. 2h27m before it was added, killed at exactly
+# 6h00m on every run since.
+assert_target amd64 hipblas llama-cpp-fallback
+assert_target arm64 hipblas llama-cpp-fallback
+
 echo "PASS: llama.cpp build target preserves CPU variants where supported"

website/content/blog/what-landed-in-localai-4-8.md

@@ -1,14 +1,14 @@
 ---
 title: "What landed in LocalAI 4.8"
-date: 2026-08-01
+date: 2026-08-04
 author: "Ettore Di Giacinto"
 category: "Release"
 tags: ["release", "vllm.cpp", "audio.cpp", "3d", "gallery", "distributed", "performance"]
-summary: "A new inference engine, 3D generation, one backend that serves six audio endpoints, and a web interface 3.48x lighter. 321 pull requests in eighteen days."
+summary: "A new inference engine, 3D generation, one backend that serves six audio endpoints, and a web interface 3.48x lighter. 374 pull requests in twenty-one days."
 extracss: ["blog.css"]
 ---
 
-LocalAI 4.8.0 is out. It took eighteen days and 321 merged pull requests, and it pulls in two directions at once: three new things LocalAI can do that it could not do before, and a long list of places where it now does the old things without lying to you.
+LocalAI 4.8.0 is out, after twenty-one days and 374 merged pull requests. There are three new things LocalAI can do, and a lot of repair work on things it already did.
 
 The full notes list everything. This post covers the parts that change what you do day to day, with the pull request numbers so you can read the diffs.
 
@@ -55,12 +55,35 @@ Every surface can override the choice: `variant` on `POST /models/apply`, `local
 
 One gap worth knowing about: in distributed mode `InstallModel` resolves against the frontend rather than the worker that will serve the model, so a cluster with a small frontend and large workers selects conservatively. PRs [#10943](https://github.com/mudler/LocalAI/pull/10943), [#10983](https://github.com/mudler/LocalAI/pull/10983), [#10992](https://github.com/mudler/LocalAI/pull/10992), [#11027](https://github.com/mudler/LocalAI/pull/11027) and [#11139](https://github.com/mudler/LocalAI/pull/11139).
 
-## A new engine: vllm.cpp
+## A new engine: vllm.cpp (alpha)
 
-[vllm.cpp](https://github.com/mudler/vllm.cpp) is a from-scratch C++20 port of vLLM, written and maintained by the LocalAI team under Apache-2.0, and it ships here as the `vllm-cpp` backend ([#11100](https://github.com/mudler/LocalAI/pull/11100)). It mirrors vLLM's V1 architecture, so paged KV cache, continuous batching, prefix caching, scheduler and sampler, on a portable tensor runtime with no Python, no PyTorch and no ggml at inference. It loads Hugging Face safetensors and GGUF, enforces structured output inside the engine (JSON schema, regex, choice, GBNF), and builds for CPU amd64 and arm64, CUDA 12 and 13 including Blackwell, L4T for GB10, Vulkan and Darwin Metal.
+[vllm.cpp](https://github.com/mudler/vllm.cpp) is Apache-2.0 and maintained by the LocalAI team. We want it community-first rather than a LocalAI-only engine, so it lives in its own repository with its own docs, benchmark record and issue tracker, and it runs without LocalAI anywhere in the picture. It began as a C++20 port of vLLM. It ships here as the `vllm-cpp` backend ([#11100](https://github.com/mudler/LocalAI/pull/11100)). It implements vLLM's V1 architecture, so paged KV cache, continuous batching, prefix caching, scheduler and sampler, on a portable tensor runtime with no Python, no PyTorch and no ggml at inference. vLLM stays its reference implementation: correctness is checked by comparing output against it, and the benchmark scoreboard is kept against it.
+
+It has grown features vLLM does not have, which is most of the reason the port exists. It loads GGUF as well as safetensors, runs on CPU, Apple Metal and Vulkan alongside CUDA 12 and 13 and L4T for GB10, and ships speculative decoding and KV offload. Its benchmark page now measures against llama.cpp, MLX-LM and DwarfStar as well as vLLM, because on that hardware those are the engines it competes with. The project is expected to be renamed, with the new name still to be decided; it is drifting far enough that vllm.cpp will eventually mislead.
 
 Tool calling is at llama.cpp parity by construction, because chat deliberately reuses the same autoparser path: full minja chat templates, `tool_choice: auto` lowered to a lazy structural-tag decode constraint, 30 tool dialects, 7 reasoning parsers, and streamed `ChatDelta` and `ToolCallDelta`.
 
+Numbers from the project's own [scoreboard](https://github.com/mudler/vllm.cpp/blob/master/docs/BENCHMARKS.md), which calls ties ties and losses losses. Above 1.0 means vllm.cpp is ahead:
+
+<div class="tw">
+<table>
+<thead><tr><th>Reference</th><th>Workload</th><th>Result</th></tr></thead>
+<tbody>
+<tr><td>vLLM</td><td>Qwen3.6-27B NVFP4, GB10</td><td>1.045x at concurrency 1, 1.007x to 1.017x from c2 to c32, output token-for-token identical</td></tr>
+<tr><td>vLLM</td><td>Qwen3.6-35B-A3B NVFP4, GB10</td><td>1.010x at c16 and 1.013x at c32, behind from c1 to c8 (0.817x at c1)</td></tr>
+<tr><td>llama.cpp</td><td>Qwen3.5-2B GGUF, CPU aarch64</td><td>prefill 1.18x, decode a tie, memory parity</td></tr>
+<tr><td>MLX-LM</td><td>Qwen3-0.6B, Apple M4</td><td>97.6% of warm total, prefill ahead</td></tr>
+<tr><td>DwarfStar (ds4)</td><td>DeepSeek-V4-Flash IQ2_XXS, one DGX Spark</td><td>16.28 vs 16.33 tok/s decode, 0.997x, a parity result</td></tr>
+</tbody>
+</table>
+</div>
+
+The upstream page is careful about its own noise: on the 27B grid the run-to-run spread is 0.5% and c2 through c32 land between 0.7% and 1.7%, so it calls those five ties rather than wins. The concurrency-1 result is the one it stands behind.
+
+The DeepSeek-V4-Flash row is the one that shows how far this has moved from being a vLLM port. It runs DeepSeek-V4-Flash at roughly 2-bit (IQ2_XXS mixed, about 80 GB) on a single DGX Spark, decoding at 16.28 tok/s against DwarfStar's 16.33. At 300B+ total parameters even a 4-bit checkpoint is 156 GB or more, so a 2-bit GGUF is what fits inside the Spark's 119 GiB unified pool, and reading GGUF is what makes that possible.
+
+Speculative decoding is in similar shape: MTP on Qwen3.6-27B NVFP4 is token-identical to vLLM's MTP and about 4% faster at concurrency 1.
+
 Configuration is a normal backend install:
 
 ```yaml
@@ -73,9 +96,24 @@ options:
 - max_num_seqs:16      # also: block_size:<n>, num_blocks:<n>
 ```
 
-The CPU path is verified end to end against `Qwen3.5-2B-UD-Q8_K_XL.gguf` with the full Ginkgo suite, covering blocking and streaming byte-parity, greedy determinism, stop words, GBNF-constrained generation, concurrent streams, reasoning split and both `required` and `auto` tool calls. The maturity statement from the release notes is worth repeating in full:
+**Treat these as alpha development builds, not a released backend.** vllm.cpp is early, and shipping it in 4.8 is about getting it in front of people who want to try it, not about recommending it for anything you care about. `llama-cpp` stays the default for real use.
 
-> The GPU images build and ship, but their runtime behavior has not been through the same e2e gate yet. This is a first release of a young engine: no throughput comparison against upstream vLLM is claimed here, and `llama-cpp` remains the default recommendation for general use. Try it, and please report what breaks.
+The CPU path is verified end to end against `Qwen3.5-2B-UD-Q8_K_XL.gguf` with the full Ginkgo suite, covering blocking and streaming byte-parity, greedy determinism, stop words, GBNF-constrained generation, concurrent streams, reasoning split and both `required` and `auto` tool calls. The GPU images build and ship, but their runtime behavior has not been through that gate. No throughput comparison against upstream vLLM is claimed. Expect rough edges, and please report what breaks.
+
+On Apple Silicon the image now ships vllm.cpp's MLX GEMM provider ([#11137](https://github.com/mudler/LocalAI/pull/11137)). Upstream keeps it off by default because it adds about 124 MB, so we measured before turning it on. Qwen3-1.7B-bf16 on an M4, p=512 g=128, both arms toggled on one binary so a build difference cannot explain the gap:
+
+<div class="tw">
+<table>
+<thead><tr><th>Batch</th><th>MLX tok/s</th><th>native tok/s</th><th>speedup</th><th>MLX TTFT</th><th>native TTFT</th></tr></thead>
+<tbody>
+<tr><td>1</td><td>5.79</td><td>3.08</td><td><b>1.88x</b></td><td>3.32 s</td><td>7.68 s</td></tr>
+<tr><td>4</td><td>15.75</td><td>10.24</td><td><b>1.54x</b></td><td>9.63 s</td><td>18.77 s</td></tr>
+<tr><td>16</td><td>38.65</td><td>17.69</td><td><b>2.19x</b></td><td>18.33 s</td><td>54.48 s</td></tr>
+</tbody>
+</table>
+</div>
+
+Two reps, with rep spread reaching 9.4%, so treat the multipliers as +/-10%. Time to first token roughly halves across the range.
 
 <figure>
 <video src="/media/vllm-race.mp4" muted loop playsinline preload="none" data-lazy aria-label="vllm.cpp generating tokens"></video>
@@ -84,7 +122,7 @@ The CPU path is verified end to end against `Qwen3.5-2B-UD-Q8_K_XL.gguf` with th
 
 ## LocalAI generates 3D models now
 
-This is a new modality rather than a new backend under an existing one, so it goes through the whole stack: a `Generate3D` RPC in `backend.proto`, a `FLAG_3D` capability so the loader knows which backends can serve it, and `POST /v1/3d/generations`.
+3D generation is a new modality, so it had to be wired through the whole stack: a `Generate3D` RPC in `backend.proto`, a `FLAG_3D` capability so the loader knows which backends can serve it, and `POST /v1/3d/generations`.
 
 The first engine behind it is `trellis2cpp`, an image-to-3D backend over TRELLIS.2. You give it an image, you get a GLB back. The web UI has a page for it with a native GLB viewer, so you can turn the result around in the browser instead of downloading it to find out whether it worked, history kept in IndexedDB so a reload does not lose your generations, and previewable print remeshing for output you actually intend to send to a printer ([#10979](https://github.com/mudler/LocalAI/pull/10979)).
 
@@ -95,7 +133,7 @@ The first engine behind it is `trellis2cpp`, an image-to-3D backend over TRELLIS
 
 ## One backend, six audio endpoints
 
-The usual shape for audio is one backend per model family, which means a process per capability and a config file for each. `audio-cpp` wraps [audio.cpp](https://github.com/0xShug0/audio.cpp), a multi-family ggml audio engine, and inverts that: one backend process serves several unrelated families through a single runtime vocabulary, and works out which family a checkpoint belongs to from the GGUF's own `audiocpp.model_spec.family` metadata key. There is nothing backend-specific to write in the model config.
+The usual shape for audio is one backend per model family, which means a process per capability and a config file for each. `audio-cpp` wraps [audio.cpp](https://github.com/0xShug0/audio.cpp), a multi-family ggml audio engine. One backend process serves several unrelated families through a single runtime vocabulary, and works out which family a checkpoint belongs to from the GGUF's own `audiocpp.model_spec.family` metadata key. There is nothing backend-specific to write in the model config.
 
 <div class="tw">
 <table>
@@ -130,7 +168,7 @@ The `bonsai` backend serves the 1-bit (Q1_0) and ternary (Q2_0) Bonsai quantizat
 
 ## The operations bar became a page
 
-The old operations bar rendered one row per in-flight operation above every page. Queue four model installs and a backend and it took most of the viewport, on every route, until the last one finished. Two things were conflated there: a global "something is happening" signal, which needs one line, and the detail of what is happening, which needs somewhere to put it.
+The old operations bar rendered one row per in-flight operation above every page. Queue four model installs and a backend and it took most of the viewport, on every route, until the last one finished. It was doing two jobs at once. A global "something is happening" signal only needs one line, and the detail of what is happening needs a page of its own.
 
 The strip is now one line, permanently, showing a failure first and otherwise the least-advanced running operation, with a `+N more` pill. Its `✕` hides the strip and no longer cancels anything. That is a deliberate behavior change worth knowing about before you click it out of habit: the same glyph used to cancel a 17 GB download in one row and dismiss a message in the next. Cancelling moved to the new page, behind a button that says so.
 
@@ -179,6 +217,6 @@ Valkey Search joins the vector store options as the `valkey-store` backend ([#11
 
 This is also the release where localai.io split in two: the project site at the root, and the documentation under `/docs/`. Every URL that was published before still resolves, through 214 generated redirect stubs, because GitHub Pages has no server-side rewrites to do it properly ([#11243](https://github.com/mudler/LocalAI/pull/11243)).
 
-Twenty-four people contributed to this release, eleven of them for the first time. The gallery went from 1,221 entries to 1,505.
+Twenty-five people contributed to this release, eleven of them for the first time. The gallery went from 1,221 entries to 1,515.
 
 To upgrade, pull `localai/localai:latest` or re-run the install script. The [full changelog](https://github.com/mudler/LocalAI/compare/v4.7.1...v4.8.0) has everything this post left out.