Jian Chen (@jianchen1799), Yesheng Liang and Zhijian Liu (@zhijianliu ) have pushed DFlash, Z Lab's block diffusion speculative decoding method, into SGLang through a collaboration with Modal and LMSYS, with the teams reporting up to 4.31x higher throughput over a non speculative baseline on Qwen 3.5 397B A17B. The June 15 release is not another model launch dressed up as infrastructure. It is a serving stack bet: if open weight frontier models keep getting larger, the bottleneck shifts from ...
source & further reading
runtimewire.com — original article
Claude Code user says the coding assistant saved his life by pushing him to the ER for AFib
Anthropic's Fable shutdown turns into a trust fight with Washington
Salesforce to buy Eoghan McCabe's Fin for about $3.6 billion