FlashDrive accelerates Alpamayo 1.5 — one of NVIDIA's 10B-parameter vision-language-action models for autonomous driving — by **4.7× with no loss in accuracy**, through streaming inference, DFlash speculative reasoning, ParoQuant W4A8 quantization, adaptive action caching, and `torch.compile`. This repository mirrors the weights of nvidia/Alpamayo-1.5-10B and is the **base checkpoint** of the FlashDrive stack. Loading it pulls the derived companions automatically: Install FlashDrive, then load this base checkpoint — the `-PARO` and `-DFlash` companions are fetched automatically:
译文排队中 · 当前显示来源原文
分类待补充
输入 待核验→ 输出 待核验
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
分类待补充
输入 待核验→ 输出 待核验
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
分类待补充
输入 待核验→ 输出 待核验
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
分类待补充
输入 待核验→ 输出 待核验
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 文本
**DFlash** is a speculative decoding method that uses a lightweight **block diffusion** model to draft multiple tokens in parallel. This is the drafter model, which must be paired with google/gemma-4-31B-it. **Setup:** Single NVIDIA B300 GPU per server/run, vLLM, thinking enabled, max output length 4096, greedy decoding. Special thanks to David Wang for his outstanding engineering support on this project. We are also grateful to Modal, InnoMatrix, and Yotta Labs for providing the compute resources used to train this draft model.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
分类待补充
输入 待核验→ 输出 待核验
**DFlash** is a novel speculative decoding method that utilizes a lightweight **block diffusion** model for drafting. It enables efficient, high-quality parallel drafting that pushes the limits of inference speed. This model serves as the **drafter** component and contains **0.8B parameters**. It must be used in conjunction with the target model `openai/gpt-oss-120b`. **gpt-oss-120b-DFlash** is trained on **800K samples**, drawn from: - `nvidia/Nemotron-Post-Training-Dataset-v2` - `theblackcat102/evol-codealpaca-v1`
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
**DFlash** is a novel speculative decoding method that utilizes a lightweight **block diffusion** model for drafting. It enables efficient, high-quality parallel drafting that pushes the limits of inference speed. This model is the **drafter** component. It must be used in conjunction with the target model `meta-llama/Llama-3.1-8B-Instruct`. **LLaMA3.1-8B-Instruct-DFlash-UltraChat** is trained on **Ultrachat-200K** and **ShareGPT** datasets, aiming to align with EAGLE-3 training data. The assistant reponses in the datasets are regenerated by `meta-llama/Llama-3.1-8B-Instruct`.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
**DFlash** is a novel speculative decoding method that utilizes a lightweight **block diffusion** model for drafting. It enables efficient, high-quality parallel drafting that pushes the limits of inference speed. This model is the **drafter** component. It must be used in conjunction with the target model `Qwen/Qwen3-4B`. This model requires `trust_remote_code=True` to load the custom architecture for block diffusion generation.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
This DFlash draft model is a joint retrain from Z-Lab and Modal, trained with 40k sequence length and sliding-window attention for improved long-context performance. It is mirrored across the following Hugging Face repositories: - `z-lab/Qwen3.5-122B-A10B-DFlash` - `modal-labs/Qwen3.5-122B-A10B-DFlash` This repository contains a DFlash draft model for `Qwen/Qwen3.5-122B-A10B`. It is not a standalone language model. It is intended to be paired with the target model in a speculative decoding server.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 文本
This DFlash draft model is a joint retrain from Z-Lab and Modal, trained with 40k sequence length and sliding-window attention for improved long-context performance. It is mirrored across the following Hugging Face repositories: This repository contains a DFlash draft model for `Qwen/Qwen3.5-4B`. It is not a standalone language model. It is intended to be paired with the target model in a speculative decoding server. DFlash uses a lightweight block diffusion draft model to propose multiple tokens in parallel. The target model verifies those proposals, improving serving throughput while preserving the target model's output distribution.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
This DFlash draft model is a joint retrain from Z-Lab and Modal, trained with 40k sequence length and sliding-window attention for improved long-context performance. It is mirrored across the following Hugging Face repositories: This repository contains a DFlash draft model for `Qwen/Qwen3.5-9B`. It is not a standalone language model. It is intended to be paired with the target model in a speculative decoding server. DFlash uses a lightweight block diffusion draft model to propose multiple tokens in parallel. The target model verifies those proposals, improving serving throughput while preserving the target model's output distribution.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 文本 · 图像→ 输出 文本
**This model is still under training, and inference engine support may not be fully available yet due to architectural changes, including causal SWA layers.** **DFlash** is a novel speculative decoding method that utilizes a lightweight **block diffusion** model for drafting. It enables efficient, high-quality parallel drafting that pushes the limits of inference speed. This model is the **drafter** component. It must be used in conjunction with the target model `Qwen/Qwen3.6-27B`.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
This DFlash draft model is a joint retrain from Z-Lab and Modal, trained with 40k sequence length and sliding-window attention for improved long-context performance. It is mirrored across the following Hugging Face repositories: - `z-lab/Qwen3.6-35B-A3B-DFlash` - `modal-labs/Qwen3.6-35B-A3B-DFlash` This repository contains a DFlash draft model for `Qwen/Qwen3.6-35B-A3B`. It is not a standalone language model. It is intended to be paired with the target model in a speculative decoding server.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
This repository contains the DFlash 2 draft model for `Qwen/Qwen3.8-27B`. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. This repository is a mirror of `incoai/Qwen3.8-27B-DFlash2`. DFlash 2 is a block-diffusion drafter for speculative decoding. It predicts a whole block of tokens in a single pass and keeps the top candidates at every position. A lightweight selector then traces one coherent path through them. Two-tap dynamic convolutions in the backbone keep the draft from decaying toward the end of the block. Decoding is lossless: greedy output matches the target model exactly, and sampling preserves its distribution. See the blog post for other engines and more details.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
This repository contains GGUF conversions of `incoai/Qwen3.8-27B-DFlash2`, the DFlash 2 draft model for `Qwen/Qwen3.8-27B`. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. This repository is a mirror of `incoai/Qwen3.8-27B-DFlash2-GGUF`. DFlash 2 is a block-diffusion drafter for speculative decoding. It predicts a whole block of tokens in a single pass and keeps the top candidates at every position. A lightweight selector then traces one coherent path through them. Two-tap dynamic convolutions in the backbone keep the draft from decaying toward the end of the block. Decoding is lossless: greedy output matches the target model exactly, and sampling preserves its distribution. Build llama.cpp with DFlash 2 support (PR #27342):
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
