[pull] master from mudler:master

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=f280b26983ad0fdb705a0d9ebf0503e76f2899b0
+LLAMA_VERSION?=eab8ee41f889ef7823af517e8098fb8a9b3cf601
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

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?=97d2990807fe6d558e395f8764198d7c7e7b411c
+STABLEDIFFUSION_GGML_VERSION?=50d640568388f876b0d63ee6ddb6bc86d997ec64
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 

core/http/endpoints/ollama/models_test.go

@@ -146,6 +146,20 @@ parameters:
 			Expect(resp.Details.Format).To(Equal("gguf"))
 			Expect(resp.Details.Families).ToNot(BeEmpty())
 		})
+
+		It("looks up the model when the Ollama :latest tag is included", func() {
+			writeConfig("chat", `
+name: chat
+backend: llama-cpp
+template:
+  chat: "{{ .Input }}"
+parameters:
+  model: Llama-3-8B-Q4_K_M.gguf
+`)
+			resp := callShow("chat:latest")
+			Expect(resp.Details.Format).To(Equal("gguf"))
+			Expect(resp.Capabilities).To(ContainElement("completion"))
+		})
 	})
 
 	Describe("ListModelsEndpoint", func() {

core/http/middleware/request.go

@@ -141,6 +141,12 @@ func (re *RequestExtractor) SetModelAndConfig(initializer func() schema.LocalAIR
 			}
 
 			modelName := input.ModelName(nil)
+			// Ollama-compat /api/tags appends ":latest" to untagged names.
+			// Strip it for lookup so the listed name works on /api/chat,
+			// /v1/chat/completions, and the other model-bearing endpoints.
+			if strings.HasSuffix(modelName, ":latest") {
+				modelName = strings.TrimSuffix(modelName, ":latest")
+			}
 			cfg, err := re.modelConfigLoader.LoadModelConfigFileByNameDefaultOptions(modelName, re.applicationConfig)
 
 			if err != nil {

core/http/middleware/request_test.go

@@ -82,6 +82,13 @@ var _ = Describe("SetModelAndConfig middleware", func() {
 			Expect(resp.Error.Message).To(ContainSubstring("not found"))
 			Expect(resp.Error.Type).To(Equal("invalid_request_error"))
 		})
+
+		It("still 404s when :latest is appended to an unknown model", func() {
+			rec := postJSON(app, "/v1/chat/completions",
+				`{"model":"nonexistent-model:latest","messages":[{"role":"user","content":"hi"}]}`)
+
+			Expect(rec.Code).To(Equal(http.StatusNotFound))
+		})
 	})
 
 	Context("when the model exists as a config file", func() {
@@ -97,6 +104,13 @@ var _ = Describe("SetModelAndConfig middleware", func() {
 
 			Expect(rec.Code).To(Equal(http.StatusOK))
 		})
+
+		It("accepts the Ollama :latest tag that /api/tags appends", func() {
+			rec := postJSON(app, "/v1/chat/completions",
+				`{"model":"test-model:latest","messages":[{"role":"user","content":"hi"}]}`)
+
+			Expect(rec.Code).To(Equal(http.StatusOK))
+		})
 	})
 
 	Context("when the model exists as a pre-loaded config", func() {

core/services/modeladmin/modeladmin_suite_test.go

@@ -2,12 +2,20 @@ package modeladmin
 
 import (
 	"testing"
+	"time"
 
 	. "github.com/onsi/ginkgo/v2"
 	. "github.com/onsi/gomega"
 )
 
 func TestModelAdmin(t *testing.T) {
 	RegisterFailHandler(Fail)
+	// Several specs in this suite coordinate goroutines through
+	// Eventually/Consistently on unbuffered-ish channels (e.g. the
+	// blockingRevisionLifecycle helper). Gomega's 1s default timeout can be
+	// too tight on slower or loaded CI runners (notably macOS runners),
+	// causing spurious "Timed out after 1.005s" failures even though the
+	// goroutines eventually make progress. Give them more headroom.
+	SetDefaultEventuallyTimeout(5 * time.Second)
 	RunSpecs(t, "modeladmin test suite")
 }