ROCm/FastFlowLM v0.9.1

## 🧪 FastFlowLM v0.9.1 — Quantization Upgrade & Log Improvements

on GitHub

FastFlowLM v0.9.1 introduces improved quantization for smaller Qwen3 models and cleaner logging in server mode.

✨ What's New

🧠 1. Improved Quantization for Qwen3 Small Models

• Switched Qwen3:0.6b and Qwen3:1.7b from manual AWQ quantization to Unsloth Q4_1.
• This improves model compatibility and performance on constrained environments.

📉 2. Optimized Server Logs

• Cleaner and more informative terminal logs in serve mode.
• Makes it easier to monitor requests, model reloads, and runtime behavior.

✅ Usage Recap

Interactive CLI:

flm run qwen3:0.6b
flm run qwen3:1.7b prompt.txt

Server Mode:

flm serve

Model Management:

flm list
flm remove qwen3:0.6b

This release continues to streamline FastFlowLM’s performance and developer experience, especially for lightweight deployment targets.