Chen Qian
Chen Qian
@Jammillk What's the Mlflow version you are using?
@JHMuir sure thing, assigned!
@TomeHirata I want to resume this one, but let me split the PR to have one dedicated on dspy.Reasoning, and a followup one to handle dspy.ChainOfThought. The previous one should...
@17Reset Thanks for reporting the issue! We are aware of this, and in an effort of shrinking the memory/time consumption at importing time. In our incoming DSPy 3.0 release, we...
`dspy.Predict` itself supports type, no need to use TypedPredictor now.
I set up the TPU test following 1, let's see how it goes in the next a few weeks.
@ryanh-ai Thanks for the suggestion! I assume you mean formatting the trajectory as multiturn message instead of a big json? I have tried it, but doesn't produce meaningful improvements. I...
@ryanh-ai Thanks! So you mean native function calling. We have noticed that native function calling yields a very poor quality, if you are interested in helping us improve DSPy, I...
@onel Thank you! Could you create a separate issue that lists out the file you are working on with the PR? thanks!
@mattdangerw My feeling is the point of accelerator testing is to test GPU compatibility, but now we are mixing GPU testing with large testing (e.g., saving). Shall we create another...