Article
How to Build a vLLM Plugin: A Guide to the general_plugins Entry Point
•
1
Jonna Matthiesen
JonnaMat
AI & ML interests
None yet
Recent Activity
liked a model about 7 hours ago
embedl/Cosmos-Reason2-2B-W4A16-Edge2-FlashHead posted an update about 16 hours ago
⚡ FlashHead benchmarks for Llama 3.2, Gemma 3, and Qwen3 are now on https://huggingface.co/spaces/embedl/Edge-Inference-Benchmarks !
These are some of the models used in the FlashHead paper - now easier to explore and compare interactively.
🚀 Jetson AGX Thor (tok/s, batch=1):
- Llama-3.2-1B: 77 → 285 (FlashHead+W4A16, 3.7x)
- Llama-3.2-3B: 34 → 112 (3.3x)
- Gemma-3-1B: 79 → 153 (1.9x)
- Qwen3-1.7B: 49 → 189 (3.8x)
- Qwen3-0.6B: 140 → 177 (1.3x)
✅ Accuracy matches baseline on MMLU-Pro, IFEval, BBH, TruthfulQA, GSM8K.
updated a model about 17 hours ago
embedl/Qwen3-1.7B-FlashHead-W4A16Organizations
published an article 6 days ago
published an article about 1 month ago
Article
FlashHead: Accelerating Language Model Inference ~ *Efficient drop-in replacement for the classification head*
•
2
published an article about 2 months ago
Article