Add batch /v1/audio/transcriptions endpoint to async apps ed2d279 aspirant312 Claude Opus 4.8 (1M context) commited on 9 days ago
Auto enforce_eager on pre-Ampere GPUs (T4 engine-core init fix) e38d105 aspirant312 Claude Opus 4.8 (1M context) commited on 10 days ago
Auto-select dtype per GPU (fix T4 engine-init crash) 2828ffe aspirant312 Claude Opus 4.8 (1M context) commited on 10 days ago
Spike: async streaming for Chughtai on vllm.AsyncLLM 4e421f1 aspirant312 Claude Opus 4.8 (1M context) commited on 10 days ago
aspirant312 Claude Opus 4.8 (1M context) commited on 
