qccl: a tiny NCCL running Ring AllReduce across 4 QwenGPU model-GPUs
zeeshanp_ · x · 2026-11-03
Claude wrote qccl, a small NCCL for QwenGPUs: each rank has a ring channel with a 2-slot FIFO and uses NCCL's Simple protocol, with all syncing done via two flags written over QLink. A video shows a Ring AllReduce across 4 QwenGPUs.
Related event: QLink: Compiling a GPU into Qwen Weights to Execute CUDA(3 posts)→
More from Infra
- China's daily token usage tops 175 trillion, now exceeding training-era totals — pstAsiatech · 2026-11-03
- GitHub macOS runners still vulnerable to eMudhra CA compromise, TLS protection ineffective — charliermarsh · 2026-11-03
- How AI assistant Sauna runs 2 million databases on Turso, 90k created daily — glcst · 2026-11-03
- MoE leaderboard shows two spikes: ~300 teams hit 2.4x using Vjeux's public kernels — Vjeux · 2026-11-03
- AMD earnings preview: cross-reading supply chain calls points to server share gains — tengyanAI · 2026-11-03
- DeepSeek-V4.1-Flash GGUF quantized build trends on Hugging Face — ISTA-DASLab · 2026-11-03