7 projects
forge-infer
Inference control plane for reasoning-aware open-source models
forge-observe
OpenTelemetry instrumentation for qwen-think reasoning sessions.
forge-infer-cloud
OpenAI-compatible reasoning-aware inference proxy for Qwen3.6
forge-dashboard
Observability dashboard for LLM inference with thinking budget and mode tracking
qwen3-repo
Architecture-aware repo-to-context scaffold for Qwen3 and Qwen3.6
qwen-think
Thinking session manager for Qwen3.6: backend normalization, sampling parameter swap, and 128K context budget guard.
qwen3.6-mtp
MTP speculative decoding tuner for Qwen3.6: vLLM/SGLang config generation, crossover analysis, and bug detection.