chore: ⬆️ Update mudler/vllm.cpp to 6738e0b4639199f3ff0998815e4d32bfa7fe5be2 (mudler#11647)

* ⬆️ Update mudler/vllm.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* fix(vllm-cpp): mirror ABI v23

The new engine pin reports ABI v23 and appends mmproj_path to
vllm_model_params. LocalAI still declares v21, so the build-time ABI
guard rejects every backend build.

Grow the Go mirror by the appended pointer and update its offset checks.
ABI v23 adds a video function but does not change the mirrored text
structs.

Assisted-by: Codex:gpt-5.6 [systematic-debugging]

---------

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: localai-org-maint-bot <bot-opensource@localaisrl.com>

Author: 3 people

backend/go/vllm-cpp/Makefile

@@ -11,7 +11,7 @@ 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?=438305e1577768ec0f75729456a4c8b9f425e2ee
+VLLM_CPP_VERSION?=6738e0b4639199f3ff0998815e4d32bfa7fe5be2
 
 # 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

backend/go/vllm-cpp/govllmcpp.go

@@ -1,6 +1,6 @@
 package main
 
-// purego bindings for the vllm.cpp stable C ABI (include/vllm.h, ABI v21).
+// purego bindings for the vllm.cpp stable C ABI (include/vllm.h, ABI v23).
 //
 // The structs below are hand-mirrored PODs of the C declarations, with
 // explicit padding so the Go layout matches the C layout on linux/darwin
@@ -21,7 +21,7 @@ import (
 // the header of the VLLM_CPP_VERSION pinned in the Makefile: the build checks
 // the two against each other, because a mismatch is only caught at runtime by
 // registerLib, where it takes the backend down on every load (issue #11379).
-const abiVersion = 21
+const abiVersion = 23
 
 // The ABI's tri-state toggles (enable_prefix_caching ABI v7,
 // enable_jump_forward ABI v10) share one encoding: 0 is NOT "off", it is
@@ -83,6 +83,7 @@ type cModelParams struct {
 	LanguageModelOnly  int32   // 0 = multimodal inputs enabled (ABI v19)
 	_                  [4]byte
 	LimitMMPerPrompt   uintptr // const char* JSON; NULL = default limits (ABI v19)
+	MMProjPath         uintptr // const char*; NULL = no GGUF projector (ABI v22)
 }
 
 // cSamplingParams mirrors vllm_sampling_params (structured fields included).

backend/go/vllm-cpp/vllmcpp_test.go

@@ -16,15 +16,15 @@ func TestVllmCpp(t *testing.T) {
 	RunSpecs(t, "vllm-cpp suite")
 }
 
-// The Go POD mirrors must match the C struct layout of vllm.h (ABI v21)
+// The Go POD mirrors must match the C struct layout of vllm.h (ABI v23)
 // byte-for-byte: these offsets are the C offsets on LP64 (linux/darwin
 // amd64+arm64). A failure here means govllmcpp.go drifted from vllm.h.
 var _ = Describe("C ABI struct mirrors", func() {
 	It("declares the ABI version the pinned engine reports", func() {
 		// VLLM_ABI_VERSION in the vllm.h of VLLM_CPP_VERSION (Makefile).
 		// Moving the pin past this without growing the mirrors below ships a
 		// backend that refuses every load at startup (issue #11379).
-		Expect(abiVersion).To(Equal(21))
+		Expect(abiVersion).To(Equal(23))
 	})
 
 	It("cModelParams matches vllm_model_params", func() {
@@ -51,7 +51,8 @@ var _ = Describe("C ABI struct mirrors", func() {
 		Expect(unsafe.Offsetof(p.KVCacheMemoryBytes)).To(Equal(uintptr(104)))
 		Expect(unsafe.Offsetof(p.LanguageModelOnly)).To(Equal(uintptr(112)))
 		Expect(unsafe.Offsetof(p.LimitMMPerPrompt)).To(Equal(uintptr(120)))
-		Expect(unsafe.Sizeof(p)).To(Equal(uintptr(128)))
+		Expect(unsafe.Offsetof(p.MMProjPath)).To(Equal(uintptr(128)))
+		Expect(unsafe.Sizeof(p)).To(Equal(uintptr(136)))
 	})
 
 	It("cSamplingParams matches vllm_sampling_params (ABI v8)", func() {