All Stories

Quantization Deep Dive: Math of GGUF, AWQ, and BitsAndBytes Double Quantization

Quantization is how a 7B model becomes a weekend desktop project instead of a dedicated server: fp16 weights are 14 GB, int8 is 7 GB, 4-bit is about 3.5 GB....

Sijin T V Sijin T V
14 Aug 2023

Optimizing RAG: BM25 + Dense Retriever Hybrid Search and Cross-Encoder Reranking

We shipped our first RAG pipeline with a single dense retriever and got paged within a week: users searching for a firmware error code like ERR_0x84F2 or a part number...

Sijin T V Sijin T V
01 Aug 2023

Optimizing Go TLS Handshake Latency for HTTP/2 Servers

What the handshake actually costs

Sijin T V Sijin T V
16 Jul 2023

Testing Complex Race Conditions and Concurrency in RSpec

The trap: a “concurrent” test that never races

Sijin T V Sijin T V
15 Apr 2023

Hardening Rails APIs: Multi-tiered Rate Limiting with Rack::Attack and Redis

Rate limiting is a liveness problem

Sijin T V Sijin T V
31 Mar 2023

Building a Custom Key-Value Store from Scratch in Go using LSM-Trees

Why the write path hates B-trees

Sijin T V Sijin T V
17 Feb 2023