[ Scrolls & chronicles ]Migration from Codea Bien
Blog
What I broke, what I measured and what I learned.
- NOV 2026AI #vllm #tool calls
Broken tool calls on vLLM, the generic hf parser and the community's #1 pain
Your agent calls a function, the model responds with the tool-call JSON, and your server parses it wrong. The agent retries, the user waits, and the support thread fills with logs.…
4 min // 200 xp
- NOV 2026AI #vllm #kv cache
The shared KV cache is an attack surface, what the SGLang leak teaches you
On October 26 the SGLang team disclosed an information leak between requests in their PD disaggregation setup. A request could end up reading another user's KV cache. The fix alrea…
4 min // 200 xp
- NOV 2026AI #vllm #kv cache
KV cache for multi-turn agents, the hidden cost of your agents
An agent talking to your API does something a 2024 chatbot didn't. It comes back. Turn 12 of the same conversation resends the previous 11 turns as context, and your inference serv…
4 min // 200 xp
- NOV 2026AI #vllm #serverless gpu
Cold starts on serverless GPU, the problem vLLM is learning to solve
Your agent receives 3 requests per hour. With a dedicated H100 pod you pay 720 hours a month to use 3. The alternative, serverless GPU, bills by the second of real GPU time, but ev…
4 min // 200 xp
- NOV 2026AI #vllm #migración
Surviving the vLLM release train, a migration guide for 2026
vLLM ships a minor version every two weeks. September brought v0.29 with Model Runner V2 as default, October brought v0.31 and v0.32 with Python 3.10 dropped and cascade attention…
5 min // 250 xp
- NOV 2026AI #vllm #sglang
vLLM vs SGLang on a rented H100, the benchmark nobody publishes
Every impressive inference number comes from racks nobody rents. GB300 NVL72, Vera Rubin, AgentX. Meanwhile, the real question for anyone renting an H100 by the hour remains undocu…
5 min // 250 xp
- OCT 2026Angular #vllm #ai
When one GPU isn't enough: multi-GPU and P/D disaggregation
Your single-GPU server runs fine until the p99 of inter-token latency spikes. The usual culprit is a 30K-token prompt arriving while ten requests are generating: everything stalls…
4 min // 200 xp
- OCT 2026AI #seo #geo
SEO, GEO, AEO: What Optimization Means When AI Answers First
I knew SEO. The terms GEO and AEO caught me by surprise; I had no idea they existed until a few months ago. And it's not like I study marketing: I've been writing code for years, b…
12 min // 600 xp
- OCT 2026Angular #vllm #ai
Speculative decoding: cut your TPOT with MTP and EAGLE-3
The number that defines whether your agent feels fast isn't throughput: it's TPOT, the time between tokens. Speculative decoding cuts it without touching the hardware, with an old…
3 min // 150 xp
- OCT 2026Angular #vllm #ai
Structured outputs and tool calling: your vLLM stops returning prose
Your vLLM server from chapter 5 returns text. An agent needs executable JSON: function names, typed arguments, fields a client can parse without a duct-taped regex. In vLLM that co…
4 min // 200 xp