Unverified50% confidenceFactExact time
FSRS has been adopted by mainstream memory software such as Anki as an optional algorithm.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFSDP reduces single-GPU memory usage by sharding model parameters, gradients, and optimizer states across multiple GPUs, and is one of the mainstream approaches for training models with hundreds of billions of parameters.64% similarUnverifiedFSDP is the officially released fully sharded data parallelism solution from PyTorch, which reduces per-device memory usage from O(N) to O(N/world_size) by sharding model parameters, gradients, and optimizer states across different devices.63% similarUnverifiedLow VRAM optimization techniques include reducing model weights from FP32 to FP16 or BF16, enabling model chunked loading and offloading to system memory, and using efficient attention implementations such as xformers or Flash Attention62% similarVerifiedGGUF is specifically optimized for CPU and hybrid CPU/GPU inference scenarios, supports memory-mapped (mmap) loading, and can run models that exceed VRAM capacity by partially offloading to system memory.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946650API
curl https://kongchang.com/api/v1/knowledge/claims/946650MCP
get_claim(id=946650)