Home Knowledge Base DFlash

DFlash

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding

arXiv:2606.02091v1 Announce Type: new Abstract: Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block simultaneously for the target model to verify in parallel. Predicting an entire block at once requires a sufficiently capable draft model and effective utilization of the target model's internal knowledge. However, the state-of-the-art method DFlash constrains all draft layers to share a single fused representation derived from only a few...

arXiv CS 8d ago

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding

arXiv:2606.02091v2 Announce Type: replace Abstract: Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block simultaneously for the target model to verify in parallel. Predicting an entire block at once requires a sufficiently capable draft model and effective utilization of the target model's internal knowledge. However, the state-of-the-art method DFlash constrains all draft layers to share a single fused representation derived from only a few...

arXiv CS 7d ago

Draft-OPD: On-Policy Distillation for Speculative Draft Models

arXiv:2605.29343v2 Announce Type: replace Abstract: Speculative decoding accelerates large language model inference by pairing a target model with a lightweight draft model whose proposed tokens are verified in parallel. A common way to build draft models, like EAGLE3 or DFlash is supervised fine-tuning (SFT) on target-generated trajectories. However, we observe that SFT quickly plateaus: the draft model's acceptance length on test data stops improving.

arXiv CS 9d ago

Cost-Aware Diffusion Draft Trees for Speculative Decoding

arXiv:2606.01813v1 Announce Type: new Abstract: Speculative decoding accelerates inference by having a lightweight drafter propose tokens verified in parallel by the target language model. Block diffusion drafters such as DFlash generate an entire draft block in one pass, yielding per-position marginals; DDTree uses these to build a candidate tree that maximizes expected acceptance length under a fixed node budget. We observe, however, that acceptance length is non-decreasing in budget: it...

arXiv CS 8d ago

MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

From the first roaring racer of the combustion age to the sonic boom that shattered the sound barrier, humanity's hunger for speed is written into our very DNA. The speed of AI reasoning is no different — it defines the boundaries of intelligence itself. When a model is fast enough, it ceases to be a tool you wait on and becomes an extension of your own thinking: responding in real time, iterating in an instant, collaborating without friction.

Hacker News 1d ago