DFlash2 news
The latest DFlash2 news, : Inco AI’s DFlash2 drafter boosts Qwen3.8-Flash-Next speed by 17%.
2 stories mentioning DFlash2 since 19 October 2026, newest first, each with its sources and discussion. Follow to see new ones on your front page.
-
Inco AI’s DFlash2 drafter boosts Qwen3.8-Flash-Next speed by 17%
Inco AI released DFlash2, an updated speculative decoding drafter for Qwen3.8-Flash-Next, offering a 17% average speedup over the original Flash-Next model. The drafter proposes token blocks in parallel and uses a…
1 source primary sourcehuggingface.co -
Ijah launches Metal‑based inference engine for Qwen 3.8‑Flash‑Next on Apple M5
The open‑source ijah engine runs on Apple M5 GPUs using raw Metal code and serves the Qwen3.8‑Flash‑Next model and its Swift‑1.5 fine‑tune via an OpenAI‑compatible HTTP API. It requires an Apple M5 Mac with Metal 4…
1 source primary sourcegithub.com
Questions about DFlash2
What is the latest DFlash2 news?
As of 30 October 2026: Inco AI’s DFlash2 drafter boosts Qwen3.8-Flash-Next speed by 17%. Inco AI released DFlash2, an updated speculative decoding drafter for Qwen3.8-Flash-Next, offering a 17% average speedup over the original Flash-Next model.