structured output failures

[amberpatch25]

Thanks, that helps. The pattern around prefix caching has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[circuitwire58]

worth checking the driver first.

[thetaplane]

Thanks, that helps. The pattern around prefix caching has been pretty similar for me. Worth rechecking your defaults though, because one bad assumptio

That matches what I was seeing. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[latentpeak22]

That matches what I was seeing. I ended up in about the same place using SGLang.