Scaling LLM Inference with Disaggregated Prefill and Decode
Disaggregated prefill/decode isn’t an academic concept it’s the fix that saved my LLM serving at scale for 40M users. Here’s exactly how it works and why mon...
Disaggregated prefill/decode isn’t an academic concept it’s the fix that saved my LLM serving at scale for 40M users. Here’s exactly how it works and why mon...
I fine tuned Phi-3 as a pairwise reranker with LoRA and logged every gradient. Early layers changed 200x more than late layers, but ranking representations o...
Auto regressive generation is sequential and diffusion uses much fewer passes in text generation.
Cross-entropy loss isn’t a heuristic, it is maximum likelihood estimation with a sign flip. It also shows how the same math powers GPT training.
Understanding the basics of RLHF vs RLAIF vs RLVR for AI feedback comparison
Master the complete pipeline for fine-tuning Large Language Models using Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) with Axolotl f...
Learning to rank with lambdarank multi objective pairwise ranking models using lightgbm
Understanding RoPE Scaling and how it enables LLMs to handle longer contexts
Basics of gradient accumulation and gradient checkpointing to train LLMs
Understanding basics of flops and how they influence gpu computation
Lessons learned from deploying large language models in productions using vLLM
Tutorial to work on large datasets in memory Polars DataFrames in Python
Understanding asyncio using simple examples in python 3.7
Learning to use FTS5 with sqlite for full text search applications
Create tfidf matrix in R just like using scikit-learn
Use pex python library to package a python project for deployment.
this line will show up as preview on the posts page
import sys a = [1,2,3] print(a)