feat: add MIND-small (distilled 6.4M student) weights + deploy graphs + card section 134fd7f verified isaaccorley commited on 25 days ago
feat: add MIND-small (distilled 6.4M student) weights + deploy graphs + card section ae96585 verified isaaccorley commited on 25 days ago
feat: add MIND-small (distilled 6.4M student) weights + deploy graphs + card section 3c98e92 verified isaaccorley commited on 25 days ago
feat: add MIND-small (distilled 6.4M student) weights + deploy graphs + card section 43bd70f verified isaaccorley commited on 25 days ago
docs: add H100 + fp8 deploy numbers; note fp8/low-rank negative results 3d6ad25 verified isaaccorley commited on 26 days ago
docs: apples-to-apples (device-I/O) deploy benchmark; TensorRT fp16 fastest aca9ed8 verified isaaccorley commited on 26 days ago
docs: add A100 deployment throughput/memory benchmark + what-to-use guide e4e9d15 verified isaaccorley commited on 26 days ago