Sam Coward
Sam Coward
Try this with `make run` and try some metrics, e.g.: ``` curl localhost:9998/metrics | grep reconcile ``` Or do some memory profiling, e.g.: ``` curl localhost:9999/debug/pprof/heap > heapdump go tool...
> @idoru thank you! have you considered having `./config/` updated? > > my first thought was of making use of an overlay in `vmware-tanzu/package-for-cartographer` that would let you configure these...
Thanks for bringing this to our attention. Can you share how many other Runnables / Workloads / Deliverables running on this cluster? Also, were there any Pod restarts on the...
What are the goals for this issue? Is raising the requirements acceptable? If the goal is reducing our memory footprint, what are the parameters for that, considering we currently know...
I was curious that there seems to be some overlap with the StdOutCallbackHandler and ConsoleCallbackHandler tracer and was curious about the design direction. Is the tracing handler intended to eventually...
Thanks for the review! I'm very new to working on Python codebases, so haven't fully got the hang of the dependency management workflows and gotchas. I'll split them as you...
Hi, thanks for the feedback. I've updated the PR now. Tested with my very amateur QLoRA model with the following: ``` MODEL_TRUST_REMOTE_CODE=true \ MODEL_LOAD_IN_4BIT=true \ MODEL_4BIT_QUANT_TYPE=nf4 \ MODEL_4BIT_DOUBLE_QUANT=true \ MODEL_PEFT=true...
Screenshots in action: https://x.com/samcoward/status/1899341240254005402