Unverified50% confidenceBenchmarkExact time
Under the synthetic settings evaluated, DASA provides a 3.6 to 4.9× speedup compared to GRADMM, with comparable peak GPU memory usage.
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedNVFP4量化方案相比BF16基线实现了1.5倍的推理加速，同时在top-1准确率上保留了92%到97%的水平71% similarUnverifiedThe best-performing Edu-QuRater achieved an average accuracy of 0.917 in reproducing GPT-4.1-mini pairwise judgments on the held-out set.67% similarUnverifiedQuantization methods such as GPTQ, AWQ, and SqueezeLLM can still maintain over 95% of the original model's performance at 4-bit precision.66% similarUnverifiedFull-parameter fine-tuning typically requires GPU memory 3–5 times the model's parameter count.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/961009API
curl https://kongchang.com/api/v1/knowledge/claims/961009MCP
get_claim(id=961009)