
Mastering LLM Quantization: Architecture and Code
From Quantization Mathematics to CUDA, Triton, Inference Runtimes, and Production Optimization
Synopsis
Om den här boken
- Språk:English
- ISBN:9781808821608
- Utgivningsdatum:18 dec. 2026
- Utgivare:Packt Publishing
- Impressum:Packt Publishing