May 02, 2026 qwen3.6-enhanced.jinja: CoT leakage into tool turns and why preserve_thinking works now Apr 29, 2026 Qwen 3.6-27B-FP8 on vLLM: enhanced.jinja, qwen3_coder, and fixing NCCL after Studio Driver 595.79 Apr 20, 2026 Qwen 3.6 35B-A3B on vLLM: do the Qwen 3.5 tool-calling fixes carry over? Apr 19, 2026 Claude Code with local vLLM: client validation, model aliases, and a working settings.json Apr 13, 2026 Stable tool calling for Qwen 3.5 27B/35B on vLLM: template, parser, and mixed-GPU fixes May 21, 2025 Workaround for Enabling NCCL P2P Communication for NVIDIA RTX 4090 Workstations Jul 13, 2024 Workaround for Debugging Windows 11 Installation