Unverified50% confidenceBenchmarkExact time
LogCDM achieves an F1 score of 0.870 on the chronologically split BGL dataset.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/10/2026
First Seen
Valid until: 2/8/2027
Sources
Related Entities
Related Claims
UnverifiedLogCDM achieves an F1 score of 0.984 on the HDFS dataset.67% similarUnverifiedSetting vLLM's gpu-memory-utilization to 0.92 under TP=4 causes OOM with the same weights, while setting it to 0.88 runs stably, because CUDA graph capture needs reserved VRAM headroom.57% similarUnverifiedThe mxfp scheme (stochastic rounding + Hadamard preprocessing) achieves 37.2K tokens/s/GPU, corresponding to 86.3% MFU, with a final training loss 2.11% higher than pure bfloat16.56% similarUnverifiedThe --gpu-memory-utilization parameter is not an upper limit on GPU memory usage, but rather the proportion of GPU memory reserved at once when vLLM starts.56% similarUnverified巨型模型存储全部权重需数TB显存,运行需要由A100或H100组成的GPU集群55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1154283API
curl https://kongchang.com/api/v1/knowledge/claims/1154283MCP
get_claim(id=1154283)