Skip to content
Tagged articles

Alibaba Qwen

4 articles · Page 1 of 1
Machine Heart
Machine Heart
Oct 23, 2026 · Artificial Intelligence

TRACE: Rollout-Guided FP4 Quantization Makes MoE RL Training Fast and Stable, 5.4× Speedup

Alibaba Qwen and Ohio State University propose TRACE, a rollout-guided quantization-aware training method that aligns training-side FP4 rounding with actual rollout quantization results, enabling stable FP4 W/A and KV cache rollout for MoE models with up to 5.4× decoding throughput gains and performance matching BF16 baselines.

Alibaba QwenFP4 quantizationMoE Models
0 likes · 9 min read
TRACE: Rollout-Guided FP4 Quantization Makes MoE RL Training Fast and Stable, 5.4× Speedup
SmartApe AI
SmartApe AI
Oct 22, 2026 · Artificial Intelligence

Kimi K3.1 Teased Officially; Qwen 4 Linked to Anonymous Arena Model Kalmia

Moonshot AI officially teases Kimi K3.1 with 1M token context and high thinking mode, while community tracker links anonymous Arena models Kibitz and Kalmia to Kimi and Qwen 4 respectively through tokenizer tests and 3D generation benchmarks.

3D generationAlibaba QwenAnonymous Model Testing
0 likes · 7 min read
Kimi K3.1 Teased Officially; Qwen 4 Linked to Anonymous Arena Model Kalmia
Senior Tony
Senior Tony
Mar 31, 2026 · Artificial Intelligence

Build and Debug LangGraph Workflows with Alibaba Qwen in Minutes

This article walks through creating a LangGraph workflow in Python, first using OpenAI’s GPT‑5‑nano model, then swapping to Alibaba’s Qwen 3.5‑plus model, showing how to suppress warnings, filter out thinking responses, visualize the graph, and troubleshoot common errors, all without any prior AI coding experience.

AI workflowAlibaba QwenLLM
0 likes · 8 min read
Build and Debug LangGraph Workflows with Alibaba Qwen in Minutes