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

Author: localai-org-maint-bot

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

@@ -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 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() {
 	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(20))
+		Expect(abiVersion).To(Equal(21))
 	})
 
 	It("cModelParams matches vllm_model_params", func() {