@tannerlinsley: Migrating asap.
Summary
Aiden Bai releases cnfast, a drop-in replacement for the cn utility that is 3x faster, and Tanner Linsley announces migrating to it.
View Cached Full Text
Cached at: 06/22/26, 01:45 PM
Migrating asap.
Aiden Bai (@aidenybai): Introducing cnfast
A 3x faster drop-in replacement for
cnnpx cnfast migrate
Similar Articles
@almoggavra: this is now deployed at Dropbox and their SlateDB startup time dropped 60x LIST calls are expensive, folk
Almog Gavra announces that a performance optimization using HEAD requests instead of LIST calls has been deployed at Dropbox, reducing SlateDB startup time by 60x.
@Zai_org: https://x.com/Zai_org/status/2057216685040443743
This paper presents ZCube, a novel network architecture developed by Z.ai, Harnets.AI, and Tsinghua University to address topology-induced congestion in Prefill-Decode disaggregated LLM inference clusters. Production deployments on GLM-5.1 coding workloads achieved a 33% reduction in network CapEx, 15% throughput improvement, and 40.6% reduction in TTFT P99 latency.
@bcherny: Guessing you're looking at npm-only data. We switched to a native installer a few months back, so the majority of insta…
An Anthropic developer corrects Andreessen Horowitz's usage metrics for Claude Code, noting that a switch to a native installer means npm data underreports actual adoption, with recent signup days showing significant growth.
@no_stp_on_snek: In progress
Promoting Atlas Inference, an open-source inference serving tool that achieved 200+ tok/s on a Qwen3.6-35B-A3B benchmark.
@zhijianliu_: This is what DFlash was built for. Our block-diffusion drafter + KV injection, now running at frontier scale — thanks t…
DFlash, a block-diffusion drafter with KV injection, is now running at frontier scale, achieving up to 4.3x greater throughput over baseline, integrated with Modal and SGLang for Qwen 397B.