Unverified50% confidenceFactExact time
The Turing architecture (RTX 20 series) Tensor Cores natively support only FP16 and not BF16; hardware acceleration for BF16 was not added until the Ampere architecture (RTX 30 series) and later
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRTX 40系列及更新架构的GPU内置了INT8和FP8运算的硬件加速单元79% similarUnverifiedThe Volta architecture Tensor Cores of the Tesla V100 only support FP16 and lack native support for BF16 and FP8.78% similarUnverifiedRTX 30系列（Ampere架构）的Tensor Core对INT4的原生支持有限，INT4运算通常需要拆包模拟75% similarUnverifiedThe 16-series Turing architecture introduced first-generation Tensor Cores supporting FP16 mixed-precision training, while the 30-series Ampere architecture upgraded to third-generation Tensor Cores and added hardware acceleration support for BF16 and TF32.74% similarUnverifiedTuring架构（对应NVIDIA RTX 20系列）是首批引入Tensor Core硬件级int8加速的消费级GPU73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/947071API
curl https://kongchang.com/api/v1/knowledge/claims/947071MCP
get_claim(id=947071)