Skip to content

DEV Community

Jasur Yuldoshev

404 bio not found

Joined on Jul 11, 2026

Jasur Yuldoshev

Aug 26

Your local RAG isn't slow — it re-reads every document on every question

#rag #llm #performance #localllama

9 min read

Jasur Yuldoshev

Aug 21

"V cache quantization requires flash_attn" — the llama.cpp error that quietly halves your context window

#llamacpp #llm #performance #debugging

10 min read

Jasur Yuldoshev

Aug 11

Streaming returned 0 tokens and llama_decode died: asyncio.wait_for was killing my generator

#python #asyncio #llm #debugging

4 min read

Jasur Yuldoshev

Jul 18

Hot-swapping GGUF models kernel-panicked my M4 Mac: wired memory, llama.cpp, and why we restart the server instead

#llm #macos #debugging #llamacpp

5 min read

Jasur Yuldoshev

Jul 13

Your Hugging Face download isn't stuck — you're being rate-limited

#huggingface #llm #machinelearning #debugging

5 min read

Jasur Yuldoshev

Jul 11

My local RAG silently returned nothing: a missing Ollama daemon, and moving embeddings in-process with llama.cpp

#ollama #python #fastapi #ai

4 min read

loading...