Developer Tools1 month ago
SuperCompress - Cut Your LLM Token Costs by 65%
Compress prompts before LLM API calls to reduce token usage and costs.
@asgujjuasitgets · X
The full gallery
Tech stack
16 projects
Compress prompts before LLM API calls to reduce token usage and costs.
@asgujjuasitgets · X
Build visual data ETL pipelines for CSV, Excel, JSON, and Parquet files in your browser.
@ashkans_dev · X
An ETL tool:
Estimate GPU memory, latency, TTFT, TPOT, and throughput for LLM inference.
popopanda · HN
LLM Inference Calculator – Estimate VRAM, Latency, and Throughput
