llama.cpp Adds DFlash Support
ggerganov · x · 2026-07-08
llama.cpp recently added DFlash support, further expanding its speculative decoding capabilities. The post also notes that alongside MTP, Eagle3, and various n-gram-based tricks, the performance of local models has taken another step forward.
More from Infra
- EdgeRock-4B holds KV cache at 72 MiB across 256K context, 99.1% smaller than Qwen3.5-4B — alifcoder · 2026-10-27
- RTX 5080 price jumps from $1658 to $2318 in ten days on Amazon — Frizzy-MacDrizzle · 2026-10-27
- ComfyUI on 12GB VRAM: measured peaks show offloading turns 24s into 11 minutes — Impossible-Mail-4619 · 2026-10-27
- Neon rebuilds its docs search entirely on its own stack: Lakebase Search, Functions, AI Gateway — matei_zaharia · 2026-10-27
- PyTorch details 2.12x faster on-device streaming ASR on Arm SME2 via ExecuTorch — PyTorch · 2026-10-27
- NVIDIA shows speculative decoding speeding up LLM inference on Jetson with Qwen3.5 9B — NVIDIA Developer · 2026-10-27