Unverified50% confidenceBenchmarkExact time
On a single H200 GPU, at 524K length RecSA achieves a 3.2x prefill speedup and a 3.8x decoding speedup.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/6/2026
First Seen
Valid until: 11/20/2026
Sources
Related Entities
Related Claims
UnverifiedThe UP host tested MiniCPM-2B on a computer with 4G VRAM and achieved a generation speed of 57 tokens per second, with a first-token latency of only 0.22 seconds.70% similarUnverifiedIn BF16 configuration (two 48GB GPUs), decoding speed ranges from 25.1 tok/s at 1K to 23.9 tok/s at 128K, with almost no degradation.68% similarUnverifiedCerebras WSE-3片上内存高达44GB SRAM,带宽达到21 PB/s,比GPU的HBM内存快约1000倍68% similarUnverifiedIn a prefill-only test running gpt-oss-120b on 4× B200s, DWDP4 achieves a 1.92× speedup over DEP4 under the MNT 32K/ISL 32K configuration and a 1.54× throughput improvement at saturation (506K vs. 329K tok/s).68% similarUnverifiedCloud-based APIs can typically achieve output speeds of tens to hundreds of tokens per second, while consumer-grade GPUs running 27B models often only reach 10–30 tokens per second.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1141967API
curl https://kongchang.com/api/v1/knowledge/claims/1141967MCP
get_claim(id=1141967)