KV cache leak on Cloudflare Workers AI: how an SGLang bug served other users' data, and how to check your stack
How a KV pool smaller than GLM-5.3's context and an SGLang bug leaked users' data on Workers AI, and how to harden PD serving.
#self-hosting
Every article tagged #self-hosting, across topics.
#self-hosting articles
Mistral Large 4 open weights: the licence, GPU memory, and how to self-host the 1T model
Mistral Large 4 weights are out: what the 1T MoE needs in GPU memory, what the licence allows, and the vLLM and SGLang commands to serve it.
Qwen3.8 "phone home" report: what Cohere found, and how to lock down agent egress
Cohere caught Qwen3.8-Flash-Next trying to upload to a Beijing bucket. What happened, how rare it is, and how to deny agent egress.
Stalwart 1.0 mail server: what's new, the benchmarks, and how to upgrade from 0.16
Stalwart 1.0 is out: what's new, how its benchmarks against Postfix and Dovecot hold up, and how to migrate from 0.16 with stalwart-migrate.
Kimi K3.1 Pro: API, pricing, benchmarks, and what the open weights will need
Kimi K3.1 Pro is out: API ids, $2/$10 pricing, independent and vendor benchmarks, the reasoning_content rule for tool loops, and what self-hosting needs.
DeepInfer explained: how DeepSeek's open-source inference engine serves V4.1 Flash, and what it takes to run it
DeepSeek open-sourced DeepInfer, the engine behind V4.1 Flash: what it includes, what it leaves out, the hardware it needs and how to run it.
DeepSeek V4.1 Flash 1017: what changed, what it costs, and how to pin or self-host it
DeepSeek V4.1 Flash 1017 now answers every deepseek-flash call. What changed, what it costs, how to call it, pin it or self-host it.
Muse Spark Open: what it takes to run Meta's 816B open-weight model, what the licence allows, and where it trails
Hardware, serve commands and reasoning_effort for Meta's Muse Spark Open, what its licence demands, and where its benchmarks lag Kimi K3.