Unverified50% confidenceBenchmarkExact time
Through request-owned speculative KV, in a DeepSeek-V4-Pro 1P1D, MI355X, concurrency-256 scenario, the average TTFT was reduced from 19.4 seconds to 15.1 seconds.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/3/2026
First Seen
Valid until: 1/1/2027
Sources
Related Entities
Related Claims
UnverifiedThe RTX 4090 has a theoretical FP16 compute performance of 330 TFLOPS, and the actual Decode speed for a 7B FP16 model is typically 50–60 tokens/s.74% similarUnverifiedIn real-world testing on an RTX 3060 (6GB VRAM) with 32GB RAM running the pre-quantized Krea2 Turbo, 1024×1024 resolution with 8-step Euler sampling achieved a speed of 1.78 s/it and a total elapsed time of 17.64 seconds.71% similarUnverified现代云内网 RTT 可低至 0.1–0.5 毫秒，与本地 SSD 的 fsync 延迟处于同一量级70% similarUnverifiedIn the DeepSeek R1 670B (MXFP4 precision) test, Jalapeño achieved approximately 1.7× throughput per watt (19,641 vs. GB300's 11,781), and end-to-end latency was reduced from 5.99 seconds to 1.65 seconds.70% similarUnverifiedAt FP16 half-precision computation, the RTX 4090 has a theoretical performance of approximately 330 TFLOPS, while the M2 Ultra's GPU delivers approximately 27.2 TFLOPS.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/969380API
curl https://kongchang.com/api/v1/knowledge/claims/969380MCP
get_claim(id=969380)