Unverified50% confidenceFactExact time
DreamDojo was trained using 256 H100 GPUs.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe NVIDIA GB300 GPU is the flagship model of the Blackwell architecture, integrating dual B200 GPU chips with a Grace CPU, delivering approximately 4x the FP8 training throughput compared to the H100.74% similarVerifiedNVIDIA's GB300 Blackwell Ultra GPU integrates two GPU chips and one Grace CPU, interconnected via NVLink-C2C, with memory bandwidth exceeding 8 TB/s and inference performance 4 to 5 times higher than the H100.68% similarUnverifiedTraining the Dota 2 AI for OpenAI Five used 256 GPUs and 128,000 CPU cores, consuming hundreds of petaflop-days of compute in total.68% similarVerifiedGrok 4.5 was trained on tens of thousands of NVIDIA GB300 GPUs, supports an ultra-long context of up to 500,000 tokens, and natively supports visual input.68% similarUnverifiedThe computing power of NVIDIA's H100/H200 GPUs is the result of the synergy between TSMC's advanced process technology and NVIDIA's CUDA architecture67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987328API
curl https://kongchang.com/api/v1/knowledge/claims/987328MCP
get_claim(id=987328)