quanglee's comments

On: Show HN: CPU-only fast OCR for screenshots, images, PDFs, webpages

[quanglee]

Do you have some benchmark on how fast it is on cpu? I checked the repo and the huggingface page but only found gpu-based benchmarks

[mrkn1 → quanglee]

I have not. My experience has been a few seconds for an 1024x1024 with medium density of text, FWIW. Feel free to try it on a few test images, model is pretty small and fast, but yeah no formal evals on CPU.

On: Show HN: Ktx – Open-source executable context layer for data agents

[quanglee]

cool idea. but for ex over time if users update db schemas, agents run old queries and got errors, is there a mechanism in your lib for agents to examine and self-correct? also is there an auto memory compression the moment the context becomes too big?

[andreybavt → quanglee]

good point! yes, there's a feedback mcp tool that agents are instructed to use when they want to save/update ktx "memories". This is a way to keep the wiki+semantic layer up to date beyond the initial ingestion. Plus every time there's a new ingestion the reconciliation mechanism will gather potentially drifting context in one place.

We don't have a manual compression yet, it's part of our other product that ktx used to be a part of before it became open-source. But we decided to move that feature to OSS too, so expect it to come out in the next releases !

On: Show HN: Tiny-vLLM – high performance LLM inference engine in C++ and CUDA

[quanglee]

love the details you put into to explain different techniques. it's a bit dense though, some schemas will help i think