What the vLLM AFD numbers ask of your interconnect
The +11.3% that vLLM's AFD plugin reports at 64A16F [s1] is a number you cannot carry to your own cluster, and the release does not publish what you would need to earn it.…
← All topics Topic
open-source LLM
Kimi K3 ranks fourth, and nobody has measured the model you would run
Every public number attached to Kimi K3 describes a rented API, not the weight file that is supposed to land on July 27. Artificial Analysis scores the model 57 on its…
Your agent attends to the right tool and still picks the wrong one
The reason your agent picked the wrong tool is almost never that your tool description was badly worded. In one 2026 study, prompt-repair recovers at most 23 percent of failures…
GLM-5.2 closes the coding gap. The catch is where you run it.
A near-frontier coding model under an MIT license reads like the moment your default flips, and that read is wrong: the license hands you the weights, not your data flow, because…
Your Context Window Is a Ceiling, Not a Budget
The context length printed on a model's spec sheet is a marketing ceiling, not an operating budget, so I size a prompt for what the model can actually use, not for what caching…
Quantizing an open model without breaking it
GPTQ, AWQ, GGUF: what quantization actually costs, measured.
Serving an open-source LLM in production: the real cost
vLLM, continuous batching, KV-cache: where the VRAM really goes.