Learn how to trace, monitor and debug #LlamaIndex applications in production and development. graphsignal.com/blog/tracing-a…

Learn how to trace, monitor and debug Hugging Face Transformers Agents in production and development. graphsignal.com/blog/tracing-h…

66% of organizations report their technology investments will be easier to justify if they support a #GenAI initiative bit.ly/3FtFKRm via Enterprise Strategy Group

Improving Information Retrieval in LLMs One effective way to use open-source LLMs is for search tasks, which could power many other applications. This work explores the use of instruction tuning to improve a language model's proficiency in information retrieval (IR) tasks.

Free ChatGPT users - what's stopping you from switching to HuggingChat?

#AI observability is evolving. Today's tools not only monitor AI performance but also unravel complex model behaviors, enhancing transparency and reliability.

Learn how to measure and analyze LLM streaming performance using time-to-first-token metrics and traces ➡️ graphsignal.com/blog/measuring…

YES, you need to see the prompts! Great article by Hamel Husain hamel.dev/blog/posts/pro…

berlin done, munich next! good crew coming too:

LLM API Latency Optimization Explained graphsignal.com/blog/llm-api-l…

Fresh dev setup on #dgx_spark running as a dstack fleet⚡️

New post: vLLM production observability - from model to hardware. graphsignal.com/blog/vllm-prod…

New post: Traditional Observability Is Blind to Inference graphsignal.com/blog/tradition…

New post: AI Debugging and Optimization For Production Inference graphsignal.com/blog/ai-debugg… Use Claude Code to debug and optimize AI systems with rich production context from Graphsignal

Now Graphsignal integrates with dstack — add SGLang profiling, tracing, and GPU metrics to your inference services. pip install 'graphsignal[cu12]' + wrap with graphsignal-run. That's it. graphsignal.com/docs/integrati…

Agent orchestration is evolving fast! Agents + orchestration + telemetry → closed-loop systems. Our friends at GraphSignal show how this unlocks continuous inference optimization in production — across heterogeneous hardware. This is where things get interesting.

Config tuning is just the start. The same loop can optimize inference code and even custom CUDA kernels. It all depends on what tools the agent can use.

autodebug by Graphsignal is a closed-loop system for inference optimization. It uses dstack to provision GPUs and redeploy services on each pass through the loop: benchmark → read profiling telemetry → tweak config → redeploy → repeat. What's interesting here is