DFlash2

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

18:59

2026-08-20

alephinitesimal.com

artificial-intelligence

Benchmarking Speculative Decoding on DGX Spark: 11.5 → 29.5 tok/s

NVIDIA's DGX Spark, powered by the GB10 superchip with 128 GB of unified LPDDR5X memory, achieves only 11.5 tokens per second running Qwen3.8-27B at Q4_K_XL quantization, limited by 273 GB/s memory ba…

00:00

2026-08-20

runagentrun.co.uk

large-language-models

Dual 3090s: the bottleneck isn't the GPU

Two benchmarks of Qwen3.8-27B on a single RTX 3090 show a 3.2x performance gap: 41.49 tok/s with llama.cpp (build b10088) versus 132 tok/s with vLLM using a DFlash2 block drafter, according to Insider…

// co-occurs with top 8 entities

Qwen3.8-27B 2 llama.cpp 2 NVIDIA 1 DGX Spark 1 GB10 1 DSpark 1 RTX 3090 1 vLLM 1

// topics top 6 topics

large language models 2 ai infrastructure 2 artificial intelligence 1 machine learning 1 ai research 1 developer tools 1