Bundle
@proton1917/dsh-live-stats
Live token estimates and generation throughput for DSH Web
Proton19171
3 results
Live token estimates and generation throughput for DSH Web
DeepSeek Harness plugin: LLM model selection & deployment analysis (deployability, VRAM, TTFT, latency, throughput, power for 38 models × 20 GPUs/NPUs)
DeepSeek Harness Web 悬浮窗:实时显示会话输出吞吐(tok/s)、本步/累计 token 与首 token 延迟,支持实时/均速双口径与多会话切换。