Register and share your invite link to earn from video plays and referrals.

filipe
@filicroval
data eng | serendipity business inquiries: filipe@filicroval.com
Joined May 2023
297 Following    153.5K Followers
Benchmarking @NVIDIAAI's Nemotron Puzzle 75B locally on the GX10. NVFP4 via vLLM's OpenAI API, MTP speculative decoding, forced 1,500-token generations. 🏃‍♀️22.75 tok/s in a single session into 88.85 cumulative at 7 sessions. 🧍Baseline without MTP: ~16.3. Scripts + setup:
Show more