Expired50% confidenceFactExact time
Huawei Cloud's ASS zero-zone computing cluster supports 100,000-card-scale computing power, compresses Token generation latency to within 10 milliseconds, and achieves computing power of 2001 PFLOPS.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
StepFun STEP3.7 Flash Tops AA Benchmark — Multimodal Reasoning Speed Takes Off
bilibiliAI天天酱6/6/2026
Related Claims
UnverifiedCollapse推理速度：CPU上单条10-token上下文约0.23毫秒，MPS在batch 1024下约230万token/秒，最近邻查询约0.48毫秒71% similarUnverified使用FWHT处理1024维向量仅需约10240次运算，而直接矩阵乘法需约100万次，接近100倍加速70% similarUnverifiedWhen running at 1-bit precision on an M2 Max equipped with 96GB of VRAM, generation speed for simple tasks is consistently around 28–30 tokens/second68% similarUnverifiedA tester ran a 20.7B dense model on a dual-4090 (48 GB VRAM) workstation and achieved 27.6 tokens per second, only slightly faster than Dwarf Star, but with over 10 times fewer parameters.68% similarUnverifiedDeepSeek V4 Flash has a rate limit of 10 requests per minute (10 RPM) and 100K tokens per minute (100K TPM) on the OpenModel platform.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/53772API
curl https://kongchang.com/api/v1/knowledge/claims/53772MCP
get_claim(id=53772)