Vedic-AI-Sovereign-Kernel / llama_runtime.log
divinesouljoy's picture
Upload llama_runtime.log with huggingface_hub
18f2c91 verified
[2026-04-14 17:20:01] INFO: Initializing llama.cpp model...
[2026-04-14 17:20:05] INFO: System: Redmi 14C (ARM64)
[2026-04-14 17:20:08] ERROR: GGML_ASSERT: failed to allocate 512.00 MB of memory for KV cache (out of memory)
[2026-04-14 17:20:12] INFO: Retrying allocation with reduced batch size...
[2026-04-14 17:20:15] DEBUG: Performing tensor multiplication (Sutra 1: Urdhva-Tiryagbhyam optimization applied)
[2026-04-14 17:20:18] error: integer overflow detected in ggml_compute_forward_mul_mat at index 4096
[2026-04-14 17:20:20] WARNING: Kernel disequilibrium detected (Sutra 14: Pitta imbalance in arithmetic pipeline)