miniTE aligns native NVFP4 reinforcement learning across engines
Authors report a Qwen3-30B-A3B learner on one B300 node at 33,540 tokens/s, 1.39× BF16 and 1.47× naive TE NVFP4.
46
Product
Transformer Engine
- Mentions · 7d0
- Mentions · 30d1
- All mentions1
- First seenOct 6, 2026
- Last mentioned24d ago
Timeline
1 articles · newest firstAppears with
- miniTEproduct · 1
- NVIDIAvendor · 1
- Qwen3-30B-A3Bai model · 1
- NVIDIA B300product · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.