Explore tools, prompts, skills, news and resources related to DFlash.
Prompt works related to DFlash
Latest articles, prompts, use cases and editorial content about DFlash
The paper proposes changing the drafting unit for speculative decoding from single target tokens to one- to three-word phrases stored in a separate draft vocabulary. A small MLP head reads the frozen target model's...
DForkTree is a training-free speculative decoding method that re-anchors block-diffusion draft-tree branches on their own tokens. It adds n-gram pointwise mutual information from the target model's outputs to drafte...
Anthropic released Claude Fable 5.2 and Mythos 5.2, claiming gains in coding, reasoning and vision, with Fable 5.2 topping the Artificial Analysis Intelligence Index at 65 and setting records on HLE-Diamond and FrontierC...
D3D is a standalone diffusion drafter that removes inter-round dependency in speculative decoding, allowing drafting of successor blocks during verification in a packed pass. It combines blockwise denoising with auxiliar...
Ricursive Intelligence has released Ripple-65B Preview, a 65B dense open-weight model pretrained from scratch for agentic coding. It achieves 80.5 on Terminal-Bench 2.1, the top self-reported score among US open-weight m...
SpecOPD introduces a branch-parallel framework for on-policy distillation in speculative decoding, enabling draft models to be trained without sequential draft-and-verify rollouts. By packing independent branches into pr...
NVIDIA has released Nemotron 3.5 Transcribe, an open-weights speech LLM that handles 40 languages and recordings up to one hour from a single model. The hybrid Mamba-Transformer MoE has roughly 34B total and 4.3B active...
Researchers from Polymathic AI, Princeton, and partners released FlashMap, a speculative decoding drafter using continuous flow maps to draft 16-token blocks in one pass. On Qwen3-8B, it reports up to 6.14x lossless spee...
NVIDIA released Nemotron 3.5 Bolt E4B, an open small language model built by RL post-training of Google's Gemma 4 E4B without supervised fine-tuning. It has 8B total and 4B effective parameters with 64K context, tar...
DeepSeek has released DeepInfer, the Apache 2.0 inference engine that powers production serving for DeepSeek-V4.1-Flash. The framework supports NVIDIA SM100 (Blackwell) GPUs and Huawei Ascend 950 NPUs and ships with Deep...
NVIDIA released Nemotron 3.5 Super VL, an open vision-language agent model with 120B total parameters and 12B active per token in a mixture-of-experts design, supporting text, image, document and video input with up to 1...
Meta Superintelligence Labs released Muse Spark Open, an 816B-parameter Mixture-of-Experts model that activates 42B parameters per token and accepts text, image, video and audio input with a 1M-token context window. Weig...
🚀 DFlash: A New Breakthrough in Flash Speculative Decoding via Block DiffusionDFlash, the latest open-source project developed by z-lab, is redefining Large Language Model (LLM) inference efficiency. By integrating...