👋 Open to Work

Prajwal Pujari

prajwalpujari16

1 14

AI & ML interests

Inference engines, LLMs, Model serving

Recent Activity

upvoted an article 3 days ago

Nemotron-Personas-Finance-Japan: A Synthetic Dataset Capturing Japan's Demographics and Financial Context

updated a dataset 4 days ago

prajwalpujari16/token-atlas-benchmark

updated a dataset 4 days ago

prajwalpujari16/llm-serving-traces

View all activity

Organizations

None yet

prajwalpujari16 's Spaces 7

RunsOnMine - Consumer Silicon LLM Serving Registry

⚡

Empirical consumer GPU serving benchmarks on Dual T4 & 3050.

mini-infer - PagedAttention KV-Cache & Prefix Studio

🚀

Interactive GPU PagedAttention block pool & prefix cache.

sched-sim - LLM Serving Scheduler & Gantt Studio

⏱

Discrete-event LLM scheduler simulator & Gantt player.

QuantBench - Sub-Byte LLM Quantization Studio

🔬

Sub-byte quantization Pareto frontier & BitNet packer.

infersize - LLM VRAM Capacity Planning CAD

⚡

Pre-flight LLM VRAM sizing CAD & cloud TCO planner.

TokenAtlas - 52-Language Token Inflation Explorer

🌐

52-language token inflation tax & fertility benchmark.

Menmo Backend

⚙