TildAlice – Tech Blog for Developers
Python, AI, Deep Learning, Data Analysis, Computer Vision, Reinforcement Learning โ tips and tutorials
Latest Posts
-
Speculative Decoding: Why 2x Faster Inference Fails
Speculative decoding promises 2x faster LLM inference, but real-world gains often disappoint. Debug the hidden bottlenecks killing your speedup.
-
LSTM Encoder-Decoder vs Seq2Seq Transformer: CMAPSS RUL Benchmark
LSTM Encoder-Decoder vs Seq2Seq Transformer on NASA CMAPSS: 18% RMSE improvement on FD004 but LSTM wins on simple data. Full PyTorch benchmark inside.
-
LangChain to LlamaIndex Migration: RAG Refactor in 5 Steps
Migrate your RAG pipeline from LangChain to LlamaIndex in 5 practical steps. Boost retrieval accuracy and simplify your LLM app architecture.
-
Pairs Trading Bot: Cointegration Test to Live Orders
Build a pairs trading bot from cointegration testing to live execution. Python stat arb strategy with Johansen test and automated order flow.
-
gc.collect() Slows Python 32%: When Manual GC Hurts
Manual gc.collect() slowed my pipeline 32%. Here's when Python's GC heuristics beat your intuition โ and the rare cases where you should override them.
-
Git Cherry-Pick Conflicts: 3 Fixes Beginners Miss
Fix Git cherry-pick conflicts fast with 3 proven methods. Learn abort, resolve, and continue strategies that save hours of debugging time.
-
ARIMA vs GARCH vs LSTM: Bitcoin Forecast Speed Benchmarks
ARIMA vs GARCH vs LSTM: Compare Bitcoin prediction speeds across statistical and deep learning models. Which wins the benchmark race?
-
TFLite vs ONNX Runtime: Pi Zero Latency at 32ms vs 89ms
Benchmark TFLite vs ONNX Runtime on Raspberry Pi Zero: which framework delivers faster inference? Latency comparison reveals clear winner.