dflash2

Here are 4 public repositories matching this topic...

0xWhiteMage / Qwen3.8-27B-Kearuga-SGLang-DGX-Spark-DFlash2

Qwen3.8-27B on one DGX Spark GB10: DFlash 2 for 65 tok/s C1 and 120 C4; EAGLE 3/1/4 for ~191 C8, ~330 C16 and ~535 C32; native 262K, pinned SGLang.

dgx qwen sglang gb10 dgx-spark dgxspark qwen3-8 dflash2

Updated Aug 21, 2026
Python

vukrosic / speculative-decoding-research

Sponsor

Star

Evidence-first lab for speculative decoding, DFlash/DFlash2, block diffusion, exactness, acceptance, and inference performance

llm-inference speculative-decoding block-diffusion dflash dflash2

Updated Aug 21, 2026
Python

47thtechcorner / RayCodes_Qwen_3.8_DFlash2

Star

Qwen 3.8 DFlash2: 27B AI Running at 236 TOK/S Locally! - High-speed local prose and code autocomplete powered by speculative decoding with lightweight draft models.

python ai transformers streamlit llm local-ai qwen speculative-decoding dflash2

Updated Aug 19, 2026
Python

CharmiUwU / Qwen3.8-27B-DFlash2-DGX-Spark

Star

DFlash2 extension of MiaAI-Lab's one-DGX-Spark Qwen3.8 NVFP4 SGLang recipe

nvidia qwen speculative-decoding sglang dgx-spark dflash2

Updated Aug 19, 2026
Python

Improve this page

Add a description, image, and links to the dflash2 topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the dflash2 topic, visit your repo's landing page and select "manage topics."

Learn more