From 4c6d5077ee912e057278438cd8bd1e448a638a5a Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Thu, 24 Sep 2026 12:07:58 +0000 Subject: [PATCH] feat(gallery): add vllm-cpp entries for laya and cua-s1-forms Add gallery entries for two vllm.cpp-backed models: - laya-vllm-cpp: multilingual non-autoregressive System 1 decision model (ModernBERT-large, 421M params). Served via POST /v1/systemone. Weights from convaiinnovations/laya (Apache-2.0). - cua-s1-forms-vllm-cpp: one-pass option scorer for GUI form filling. Served via POST /api/score. Weights from cua-ai/cua-s1-forms (MIT). Both entries set backend: vllm-cpp and declare CPU+GPU tags. Assisted-by: Maki:regolo/glm5.2 [maki] Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 74 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 73 insertions(+), 1 deletion(-) diff --git a/gallery/index.yaml b/gallery/index.yaml index cbf99f782..84b0433e6 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -62288,7 +62288,7 @@ files: - filename: OpenResearcher-30B-A3B-Q4_K_M.gguf uri: huggingface://OpenResearcher/OpenResearcher-30B-A3B-GGUF/OpenResearcher-30B-A3B-Q4_K_M.gguf - sha256: 2ac3981624ca76c1e3eca569b649cf041e91ad8c95ac6b2cc41897881d773c08 + sha256: 2ac3981624ca76c1e3eca569b649cf041d91ad8c95ac6b2cc41897881d773c08 - name: "openresearcher-30b-a3b-q8" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: @@ -62317,3 +62317,75 @@ - filename: OpenResearcher-30B-A3B-Q8_0.gguf uri: huggingface://OpenResearcher/OpenResearcher-30B-A3B-GGUF/OpenResearcher-30B-A3B-Q8_0.gguf sha256: c216d75002a580f939ceaf944965b0d4fd7d7b5b29a0914a001d836e49866970 +- name: laya-vllm-cpp + url: github:mudler/LocalAI/gallery/virtual.yaml@master + urls: + - https://huggingface.co/convaiinnovations/laya + - https://github.com/mudler/vllm.cpp + description: | + Laya is a multilingual, non-autoregressive System 1 decision model. + Given a state (text, email, ticket, or JSON) and typed questions, it + returns typed answers with mathematically calibrated probabilities in a + single forward pass. It never generates text, so there is nothing to + parse and nothing to hallucinate. + + In LocalAI, serve via POST /v1/systemone with this model. The vllm.cpp + engine runs the full decision pipeline (choice, noul, score question + types) through the vllm_decide C ABI, returning the complete + kev-compatible JSON response. ModernBERT-large backbone, 421M params, + 512-token context. F16 weights, ~804 MB. + license: apache-2.0 + tags: + - decision + - systemone + - vllm-cpp + - cpu + - gpu + size: 804MB + last_checked: "2026-09-21" + overrides: + backend: vllm-cpp + known_usecases: + - chat + parameters: + model: convaiinnovations/laya + artifacts: + - name: model + target: model + source: + type: huggingface + repo: convaiinnovations/laya +- name: cua-s1-forms-vllm-cpp + url: github:mudler/LocalAI/gallery/virtual.yaml@master + urls: + - https://huggingface.co/cua-ai/cua-s1-forms + - https://github.com/mudler/vllm.cpp + description: | + cua-s1-forms is a small, jev-like ("System One") one-pass option scorer + for GUI form filling. Given a UI element and a list of typed options, + it returns one probability per option in a single forward pass. Every + actionable element on a form is scored independently and in parallel. + + In LocalAI, serve via POST /api/score with this model. The vllm.cpp + engine runs the scoring pipeline through the vllm_decide C ABI. 2.8 MB, + float32, CPU and GPU. + license: mit + tags: + - scoring + - vllm-cpp + - cpu + - gpu + size: 3MB + last_checked: "2026-09-21" + overrides: + backend: vllm-cpp + known_usecases: + - score + parameters: + model: cua-ai/cua-s1-forms + artifacts: + - name: model + target: model + source: + type: huggingface + repo: cua-ai/cua-s1-forms