feat(dllm): backend packaging, gallery index, CI matrix

Registers the dllm backend across every surface: backend gallery index (cpu amd64+arm64 with manifest merge, cuda13, l4t-cuda13 for GB10-class hardware; no darwin per engine scope), top-level Makefile targets, bump_deps pin tracking for DLLM_VERSION, and the curated known-backends list for /backends/known (pref-only: auto-detecting on .gguf would shadow llama-cpp). Note: image builds and the nightly bump leg stay red until github.com/mudler/dllm.cpp is published (planned at merge time). Assisted-by: Claude Code (Fable 5) Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-08-04 12:22:22 -04:00 · 2026-06-11 17:05:18 +00:00
parent 9a8cc3c5e7
commit 845e24f61b
8 changed files with 107 additions and 3 deletions
--- a/.github/backend-matrix.yml
+++ b/.github/backend-matrix.yml
@@ -1911,6 +1911,19 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-dllm'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "dllm"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
  - build-type: 'cublas'
    cuda-major-version: "13"
    cuda-minor-version: "0"
@@ -1924,6 +1937,19 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-cuda-13-arm64-dllm'
+    base-image: "ubuntu:24.04"
+    ubuntu-version: '2404'
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "dllm"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
  - build-type: 'cublas'
    cuda-major-version: "13"
    cuda-minor-version: "0"
--- a/.github/workflows/bump_deps.yaml
+++ b/.github/workflows/bump_deps.yaml
@@ -50,6 +50,10 @@ jobs:
            variable: "PARAKEET_VERSION"
            branch: "master"
            file: "backend/go/parakeet-cpp/Makefile"
+          - repository: "mudler/dllm.cpp"
+            variable: "DLLM_VERSION"
+            branch: "main"
+            file: "backend/go/dllm/Makefile"
          - repository: "mudler/vllm.cpp"
            variable: "VLLM_CPP_VERSION"
            branch: "main"
--- a/6
+++ b/6
@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/bonsai backends/outetts backends/piper backends/stablediffusion-ggml backends/trellis2cpp backends/trellis2cpp-darwin backends/whisper backends/crispasr backends/parakeet-cpp backends/moss-transcribe-cpp backends/faster-whisper backends/silero-vad backends/local-store backends/valkey-store backends/cloud-proxy backends/huggingface backends/rfdetr backends/rfdetr-cpp backends/insightface backends/speaker-recognition backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/longcat-video backends/sglang backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros backends/sam3-cpp backends/qwen3-tts-cpp backends/moss-tts-cpp backends/magpie-tts-cpp backends/vllm-cpp backends/omnivoice-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio backends/supertonic backends/depth-anything-cpp backends/privacy-filter backends/privacy-filter-darwin
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/bonsai backends/outetts backends/piper backends/stablediffusion-ggml backends/trellis2cpp backends/trellis2cpp-darwin backends/whisper backends/crispasr backends/parakeet-cpp backends/dllm backends/moss-transcribe-cpp backends/faster-whisper backends/silero-vad backends/local-store backends/valkey-store backends/cloud-proxy backends/huggingface backends/rfdetr backends/rfdetr-cpp backends/insightface backends/speaker-recognition backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/longcat-video backends/sglang backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros backends/sam3-cpp backends/qwen3-tts-cpp backends/moss-tts-cpp backends/magpie-tts-cpp backends/vllm-cpp backends/omnivoice-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio backends/supertonic backends/depth-anything-cpp backends/privacy-filter backends/privacy-filter-darwin

 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -1271,6 +1271,9 @@ BACKEND_TRELLIS2CPP = trellis2cpp|golang|.|--progress=plain|true
 BACKEND_WHISPER = whisper|golang|.|false|true
 BACKEND_CRISPASR = crispasr|golang|.|false|true
 BACKEND_PARAKEET_CPP = parakeet-cpp|golang|.|false|true
+# dllm is mudler/dllm.cpp, the DiffusionGemma block-diffusion engine,
+# wrapped by the purego backend at backend/go/dllm.
+BACKEND_DLLM = dllm|golang|.|false|true
 BACKEND_MOSS_TRANSCRIBE_CPP = moss-transcribe-cpp|golang|.|false|true
 BACKEND_DEPTH_ANYTHING_CPP = depth-anything-cpp|golang|.|false|true
 BACKEND_VOXTRAL = voxtral|golang|.|false|true
@@ -1372,6 +1375,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_TRELLIS2CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_WHISPER)))
 $(eval $(call generate-docker-build-target,$(BACKEND_CRISPASR)))
 $(eval $(call generate-docker-build-target,$(BACKEND_PARAKEET_CPP)))
+$(eval $(call generate-docker-build-target,$(BACKEND_DLLM)))
 $(eval $(call generate-docker-build-target,$(BACKEND_MOSS_TRANSCRIBE_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_DEPTH_ANYTHING_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_VOXTRAL)))
--- a/backend/go/dllm/Makefile
+++ b/backend/go/dllm/Makefile
@@ -14,6 +14,10 @@
 # That's what the gated C-ABI binding smoke uses (DLLM_TEST_LIBRARY). The
 # default target below does the proper clone-at-pin + cmake build so CI
 # doesn't need a side-checkout.
+#
+# NOTE: github.com/mudler/dllm.cpp is still private (publishing is planned);
+# until then the anonymous clone below fails. Use the symlink shortcut above
+# with a local checkout, or a git credential helper with access to the repo.

 DLLM_VERSION?=b22fcebebfb225131113188599a9ae542b2935d7
 DLLM_REPO?=https://github.com/mudler/dllm.cpp
--- a/backend/go/dllm/dllm.go
+++ b/backend/go/dllm/dllm.go
@@ -275,8 +275,8 @@ func (d *Dllm) requestOptsJSON(opts *pb.PredictOptions) (string, error) {
 		// The engine rounds n_predict UP to a whole number of diffusion
 		// blocks (the canvas is denoised block-wise), so the completion may
 		// run slightly past the requested budget. Tokens==0 omits the key so
-		// the engine's GGUF-metadata default applies (the C-ABI documents
-		// per-key defaults; no hardcoded 256 like ds4's grpc-server).
+		// the C-ABI default of 256 applies (hardcoded in capi.cpp's
+		// parse_gen_opts, independent of canvas_length).
 		m["n_predict"] = n
 	}
 	if s := opts.GetSeed(); s > 0 {
--- a/backend/index.yaml
+++ b/backend/index.yaml
@@ -129,6 +129,29 @@
    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-ds4"
    metal: "metal-ds4"
    metal-darwin-arm64: "metal-ds4"
+- &dllm
+  name: "dllm"
+  alias: "dllm"
+  license: mit
+  description: |
+    mudler/dllm.cpp - DiffusionGemma block-diffusion LLM inference engine
+    (C++/ggml, GGUF weights). Decodes whole token canvases per diffusion
+    round instead of autoregressive sampling. Runs on CPU and NVIDIA CUDA 13
+    (including Jetson/GB10 L4T targets).
+  urls:
+    - https://github.com/mudler/dllm.cpp
+  tags:
+    - text-to-text
+    - LLM
+    - gguf
+    - diffusion
+    - CPU
+    - CUDA
+  capabilities:
+    default: "cpu-dllm"
+    nvidia: "cuda13-dllm"
+    nvidia-cuda-13: "cuda13-dllm"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-dllm"
 - &whispercpp
  name: "whisper"
  alias: "whisper"
@@ -2001,6 +2024,13 @@
    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-ds4-development"
    metal: "metal-ds4-development"
    metal-darwin-arm64: "metal-ds4-development"
+- !!merge <<: *dllm
+  name: "dllm-development"
+  capabilities:
+    default: "cpu-dllm-development"
+    nvidia: "cuda13-dllm-development"
+    nvidia-cuda-13: "cuda13-dllm-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-dllm-development"
 - !!merge <<: *stablediffusionggml
  name: "stablediffusion-ggml-development"
  capabilities:
@@ -2858,6 +2888,37 @@
  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-ds4"
  mirrors:
    - localai/localai-backends:master-metal-darwin-arm64-ds4
+## dllm
+- !!merge <<: *dllm
+  name: "cpu-dllm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-dllm"
+  mirrors:
+    - localai/localai-backends:latest-cpu-dllm
+- !!merge <<: *dllm
+  name: "cpu-dllm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-dllm"
+  mirrors:
+    - localai/localai-backends:master-cpu-dllm
+- !!merge <<: *dllm
+  name: "cuda13-dllm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-dllm"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-dllm
+- !!merge <<: *dllm
+  name: "cuda13-dllm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-dllm"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-dllm
+- !!merge <<: *dllm
+  name: "cuda13-nvidia-l4t-arm64-dllm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-dllm"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-dllm
+- !!merge <<: *dllm
+  name: "cuda13-nvidia-l4t-arm64-dllm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-dllm"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-dllm
 ## whisper
 - !!merge <<: *whispercpp
  name: "whisper-development"
--- a/core/http/endpoints/localai/backend.go
+++ b/core/http/endpoints/localai/backend.go
@@ -30,6 +30,10 @@ var knownPrefOnlyBackends = []schema.KnownBackend{
 	// core/gallery/importers/privacy-filter.go); the importer registry entry
 	// supersedes any pref-only line here, which the /backends/known merge would
 	// dedupe away.
+	// dllm consumes GGUF weights like llama-cpp does, but only for the
+	// DiffusionGemma architecture - auto-detecting on .gguf would shadow
+	// llama-cpp, so it stays preference-only.
+	{Name: "dllm", Modality: "text", AutoDetect: false, Description: "dllm.cpp DiffusionGemma block-diffusion engine (preference-only)"},
 	{Name: "sglang", Modality: "text", AutoDetect: false, Description: "SGLang runtime (preference-only)"},
 	{Name: "tinygrad", Modality: "text", AutoDetect: false, Description: "tinygrad runtime (preference-only)"},
 	{Name: "trl", Modality: "text", AutoDetect: false, Description: "Transformers Reinforcement Learning (preference-only)"},
--- a/core/http/endpoints/localai/backend_test.go
+++ b/core/http/endpoints/localai/backend_test.go
@@ -148,6 +148,7 @@ var _ = Describe("Backend Endpoints", func() {
 				Expect(entry.Modality).To(Equal(modality))
 			}

+			expectPrefOnly("dllm", "text")
 			expectPrefOnly("sglang", "text")
 			expectPrefOnly("tinygrad", "text")
 			expectPrefOnly("trl", "text")