Ornith-1.0-9B-DSpark is a production-qualified DSpark speculative-decoding draft for deepreinforce-ai/Ornith-1.0-9B. This repository contains the draft/speculator only. It is not a standalone language model. The draft must be paired with the exact Ornith verifier revision described in candidate-manifest.json. When served through speculative decoding, the verifier remains the source of truth for outputs and model capability; this draft proposes token blocks that the verifier accepts or rejects. Large training logs, intermediate checkpoints, handoff notes, local deployment experiments, and raw evaluation dumps are intentionally not included. All measurements were run against the matched Ornith verifier on NVIDIA B200 hardware with the serving configuration represented in this repository. The speed figures are specific to the tested Ornith/B200/vLLM stack. Different GPUs, batching policies, vLLM versions, or target revisions require fresh profiling and qualification. The draft repository is about 6.2 GiB. The Ornith verifier is a separate download and is not duplicated here. The qualified runtime uses DSpark support that is not assumed to exist in an unmodified stable vLLM release.…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: stanleyphoong
Теги: qwen3_5, speculative-decoding, dspark, dflash, qwen3.5, vllm, custom-code, model-index
Лайков: 3 | Загрузок: 73
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
