Gpu
Gpu
- Epilog GPU Validator
Drain a node for a persistently faulty GPU — and never for a transient one.
- GPU Reaper
Find wasted GPU allocations on a Slurm cluster and escalate them through alert, drain, and cancel.
- Your Slurm Priority Weights Matter Less Than Your Users' Time Limits
I built a simulator to tune Slurm priority weights. It kept telling me the weights were not the problem.
- vLLM vs TensorRT-LLM: First Throughput Numbers on Llama-3 70B
Quick benchmark comparing vLLM and TensorRT-LLM throughput on a single A100 80GB with Llama-3 70B. Setup notes, raw numbers, and what I'd investigate next.
- How KV-Cache Paging Works in vLLM — and Why It Matters for Production
A technical walkthrough of PagedAttention: the memory management innovation that makes vLLM practical for serving many concurrent LLM sessions without fragmenting GPU memory.
- Agentic ML Inference Infrastructure
Production agentic AI infrastructure layer: autonomous systems that reason, decide, and act on real workloads using vLLM, LangGraph, and MCP.
- 128-GPU Distributed Training Platform
Distributed ML training infrastructure for large-scale models: FSDP, gradient checkpointing, mixed precision, and cost-optimized multi-node orchestration.
- GPU-Accelerated Volatility Surface Calibration
CUDA-accelerated local and stochastic volatility surface calibration — Dupire's model, Heston, and hybrid approaches for real-time derivatives pricing.