npgraph
CUDA Profiler for Production Inference
Re:DeepSeek 4 Flash local inference engine for Metal
on Friday May 08, 2026 @10:21AM (#48063669)
Any direct TPS comparison to Ollama?
Autodebug: Telemetry-Driven Inference Optimization Loop
AutoGPT Tracing: Prompts, Costs, Latency, Compute
Monitor OpenAI API Latency, Tokens, Rate Limits, Costs
Monitoring and Tracing LangChain Applications
Show HN: Python Monitoring for LLMs, OpenAI, Inference, GPUs
https://github.com/graphsignal/graphsignal-python
Hi HN. I'm excited to share our AI-focused application monitoring and analytics for Python! We've built it for apps that use LLMs and other ML models. The lightweight Python agent autoinstruments OpenAI, LangChain, Banana, and other APIs and frameworks. Basically by adding one line of code you'll be able to monitor and analyze latency, errors, compute and costs. Profiling using CProfile,...
Show HN: Python Monitoring for AI: LLMs, OpenAI, Inference, GPUs
https://github.com/graphsignal/graphsignal-python
Hi HN. I'm excited to share our AI-focused application monitoring and analytics for Python!We've built it for apps that use LLMs and other ML models. The lightweight Python agent autoinstruments OpenAI, LangChain, Banana, and other APIs and frameworks. Basically by adding one line of code you'll be able to monitor and analyze latency, errors, compute and costs. Profiling using CProfile, PyTorch...
Monitoring and Tracing LangChain Applications
Re:Monitor OpenAI API Latency, Tokens, Rate Limits, and More
on Tuesday January 31, 2023 @08:36AM (#34594829)
Relying on hosted inference with LLMs, such as via OpenAI API, in production has some challenges. The use of APIs should be designed around unstable latency, rate limits, token counts, costs, etc. To make it observable we've built tracing and monitoring specifically for AI apps. For example, the OpenAI Python library is monitored automatically, no need to do anything. We'll be adding support for more libraries. If you'd like to give it try, see https://github.com/graphsignal/graphsignal or the docs.