Unverified50% confidenceBenchmarkExact time
According to ZDNet Korea, VIDRAFT officially announced: on the same NPU, after enabling VKORE, single-user inference latency improved 3.8x, concurrent server throughput improved 4.1x, and training throughput was about 170x compared with a CPU baseline.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/13/2026
First Seen
Valid until: 10/27/2026
Sources
Related Entities
Related Claims
UnverifiedVKORE increases single-user inference response speed by 3.8x on the same NPU hardware.75% similarUnverifiedVIDRAFT's VKORE software acceleration layer, without changing the chip, both increases NPU inference performance several times over and makes Transformer LoRA training run on this kind of inference-specific hardware, with numerical precision aligned with standard PyTorch at 0.9999.64% similarUnverifiedAccording to reports, in CoreWeave's tests, the isolated sandbox environment for running code starts more than 3x faster on the new Vera CPU64% similarUnverifiedThe HD Noise Canceling Processor QN1 used in the Sony XM4 performs more than 700 operations per second.62% similarUnverifiedFreeToken achieves inference speeds 3 times faster than Ollama under the same hardware conditions.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1022381API
curl https://kongchang.com/api/v1/knowledge/claims/1022381MCP
get_claim(id=1022381)