Unverified50% confidenceBenchmarkExact time
B200采用Blackwell架构，引入第二代Transformer Engine和FP4精度支持，推理吞吐量较H100提升最高30倍
1
Sources
50%
Confidence
Long-term
Relevance
8/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBlackwell's second-generation Transformer Engine adds FP4 precision support, which in theory can improve Transformer model training throughput by 2–4x compared to the H100.80% similarUnverifiedThe H100 GPU is based on the Hopper architecture; its Transformer Engine can dynamically switch between FP8 and FP16 precision, boosting throughput to approximately 2–3 times that of the A100.72% similarVerifiedCore innovations of the Blackwell architecture include the second-generation Transformer Engine (supporting FP4 precision), the NVLink Switch system (supporting interconnection of 576 GPUs), 20 petaFLOPS of FP4 compute, and 192 GB HBM3e memory (with bandwidth reaching 8 TB/s).72% similarUnverifiedThe Hopper architecture of the H100 introduced a dedicated Transformer Engine supporting FP8 precision computation.72% similarVerifiedNVIDIA's H100 features a Transformer Engine specifically designed for AI workloads, delivering nearly 4,000 TFLOPS of compute at FP8 precision, approximately 3 times the improvement over the A100.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/811461API
curl https://kongchang.com/api/v1/knowledge/claims/811461MCP
get_claim(id=811461)