AAkshay Suryawanshi·Oct 16From Replicas to FP8: My First vLLM Performance InvestigationTesting vLLM replicas, NVIDIA MPS, and FP8 KV cache and attention on one laptop GPU, measuring throughput, latency, goodput, and answer quality.10 min read·akshaysuryawanshi.hashnode.dev
MMuhammad Tahir·Oct 12Model Distillation & Quantization: Running 8B Parameter Models at a Fraction of Cloud CostThis article was originally published on Muhammad Tahir's Portfolio. Introduction & Industry Context In the production AI landscape of 2026, enterprise architectures are undergoing a decisive paradigm13 min read·mtdeveloper.hashnode.dev
