chore: ⬆️ Update mudler/vllm.cpp to 76f2a6d84e41cc9a593146a9a958f63645542731 (#11555)

* ⬆️ Update mudler/vllm.cpp

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

* fix(vllm-cpp): track ABI v21

The updated engine exposes ABI v21 after extending its speech API. The Go
backend does not bind that API, so its existing mirrors remain valid.

The qwen3.5 warning fix is now present upstream, so the old patch no
longer applies.

Assisted-by: Codex:gpt-5

---------

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 <306269227+localai-org-maint-bot@users.noreply.github.com>

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?=4880c5715f36445a30bd39d3349a06dc96085a11
+VLLM_CPP_VERSION?=76f2a6d84e41cc9a593146a9a958f63645542731
 
 # 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 v20).
+// purego bindings for the vllm.cpp stable C ABI (include/vllm.h, ABI v21).
 //
 // 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 = 20
+const abiVersion = 21
 
 // 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

backend/go/vllm-cpp/patches/0001-fix-qwen35-unused-lambda-capture.patch

@@ -1,26 +0,0 @@
-From: LocalAI maintainers
-Subject: [PATCH] fix(qwen3.5): drop redundant kRequired capture
-
-Apple Clang diagnoses the capture of this namespace-scope reference as unused,
-and vllm.cpp promotes that warning to an error. The lambda can access the name
-without a capture.
-
-Retire this patch when the pinned vllm.cpp revision no longer captures
-kRequired in the qwen3.5 refusal lambda.
----
- src/vllm/model_executor/models/qwen3_5_weights.cpp | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/src/vllm/model_executor/models/qwen3_5_weights.cpp b/src/vllm/model_executor/models/qwen3_5_weights.cpp
-index 7150443..7de1b9d 100644
---- a/src/vllm/model_executor/models/qwen3_5_weights.cpp
-+++ b/src/vllm/model_executor/models/qwen3_5_weights.cpp
-@@ -950,7 +950,7 @@ void CheckMoeQuantLayoutSupported(const std::vector<std::string>& names,
-   // ...and the three NON-routed components, refused by the dtype the probe
-   // RESOLVED rather than discovered as a complaint from inside a reader (#490).
-   // Each of these already failed before #864; naming it is the whole change.
--  const auto refuse = [&kRequired](const char* what, MoeProjDtype got,
-+  const auto refuse = [](const char* what, MoeProjDtype got,
-                                    const char* supported) {
-     VT_CHECK(false, std::string("qwen3_5 weights: a ") +
-                         MoeProjDtypeName(got) + " " + what +

backend/go/vllm-cpp/vllmcpp_test.go

@@ -16,7 +16,7 @@ func TestVllmCpp(t *testing.T) {
 	RunSpecs(t, "vllm-cpp suite")
 }
 
-// The Go POD mirrors must match the C struct layout of vllm.h (ABI v20)
+// The Go POD mirrors must match the C struct layout of vllm.h (ABI v21)
 // 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() {
@@ -24,7 +24,7 @@ var _ = Describe("C ABI struct mirrors", 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(20))
+		Expect(abiVersion).To(Equal(21))
 	})
 
 	It("cModelParams matches vllm_model_params", func() {