Fixing Tool-Call Accuracy in vLLM(ubicloud.com)
41 points by coffeemug | 6 comments
Ubicloud blog post explaining tool-call schema accuracy problems when serving open-weight models like Kimi K2.6 in vLLM and how constrained decoding fixes them.
10 stories tagged kimi, newest first.
41 points by coffeemug | 6 comments
Ubicloud blog post explaining tool-call schema accuracy problems when serving open-weight models like Kimi K2.6 in vLLM and how constrained decoding fixes them.
47 points by nekofneko | 5 comments
Moonshot AI blog post announcing Kimi K3.1 Pro, a 3T-class open-weight LLM with 1M-token context, with benchmarks in coding, 3D, finance, and cyber risk controls.
1066 points by Jowsey | 655 comments
Kimi Code documentation page on model configuration, introducing K3.1 Pro and K3.1 Pro Highspeed and covering model IDs, plans, switching, and third-party API setup.
469 points by monneyboi | 138 comments
Kimi Code documentation page describing available models (Kimi K3 and Kimi K2.7 Code), their model IDs, and how to switch between them in clients.
660 points by ms7892 | 269 comments
Product page for Kimi Work, Moonshot AI's AI desktop application for knowledge work, with a download button showing it is not available for the visitor's system.
1981 points by vincent_s | 1153 comments
Moonshot AI's Kimi blog post announcing the Kimi K3 open frontier model; the captured page shows only the Kimi chat interface.
388 points by unliftedq | 162 comments
GitHub changelog post announcing that the Kimi K2.7 Code model is generally available as a model choice in GitHub Copilot.
389 points by nekofneko | 208 comments
Hugging Face model card for Moonshot AI's Kimi-K2.7-Code, an open-weights 1T-parameter coding model released under a modified MIT license.
613 points by meetpateltech | 322 comments
Kimi blog post announcing Kimi K2.6, an open-source large language model focused on improved coding capabilities.
423 points by nekofneko | 199 comments
Blog post announcing Kimi K2.5, an open-source native multimodal model with coding, vision, and agent swarm capabilities.