Unverified50% confidenceSolutionExact time
In mixed-precision training, the forward pass uses FP16 to leverage Tensor Core acceleration while parameter updates retain FP32 to maintain numerical stability, which has become standard practice for large model training.
1
Sources
50%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
UnverifiedMixed-precision training was jointly proposed by NVIDIA and Baidu in 2018; its core idea is to use FP16 in forward and backward propagation to reduce VRAM usage and accelerate computation, while retaining an FP32 master weight copy for parameter updates.78% similarUnverifiedMixed precision training can theoretically reduce memory usage by nearly half and achieve 2–8× computational speedup on GPUs that support Tensor Cores, such as T4, V100, and A100.78% 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 TF32.78% similarUnverified混合精度训练由 NVIDIA 在 2018 年提出，同时使用 FP32 和 FP16 两种精度76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/592547API
curl https://kongchang.com/api/v1/knowledge/claims/592547MCP
get_claim(id=592547)