Q4_0, Q8_0 and mixed files for Krafla, CPU inference in C11 from SSE2 to AVX-512 and ARMv7 NEON to SVE.
Yeo Choon, Park
jonpark0
AI & ML interests
Edge AI on NPUs: converting and running models on Axera AX650 / AX8850 (LLM-8850). Robotics and embedded hardware.
Recent Activity
updated a model 2 days ago
jonpark0/TinyLlama-1.1B-Chat-v1.0-krafla updated a model 2 days ago
jonpark0/SmolLM2-360M-Instruct-krafla updated a model 2 days ago
jonpark0/SmolLM2-135M-Instruct-kraflaOrganizations
None yet