dsh-live-perf-gauges
用于 DeepSeek Harness Web 的实时解码、TTFT、提示速率和 MTP 流式仪表。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:TnzGit/dsh-live-perf-gauges#c667551e556ef48fb954246218824fa459b3398fLive Perf Gauges 以 dsh-live-perf-gauges 发布，当前版本为 0.2.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
An automotive-style live performance strip for DeepSeek Harness Web: decode throughput, TTFT, effective prompt rate, stream-event/MTP diagnostics, and output-token progress under the composer.
step/start to the first streamed text, reasoning, or tool-argument delta.input + cache read + cache write) divided by end-to-end TTFT. It is deliberately not labelled as vLLM kernel prefill throughput because it includes DSH overhead, network/queue time, and cached tokens.One SSE event is never assumed to equal one token. This matters for speculative decoding: an accepted MTP group can deliver several generated tokens in one streamed event.
The plugin never contacts a network service and never stores message text, prompts, tools, or credentials. It only projects timestamps, counts, and final token usage already present in the session event stream.
dsh plugin --profile web add github:TnzGit/dsh-live-perf-gauges
Restart the running dsh web service, then hard-refresh the browser. The strip appears below the composer after the next model step begins.
Designed for the DSH 0.1.x Web profile and its standard conversation.composer.dock, sessionProjections, and contextPressure interfaces.
npm test
This repository ships prebuilt dependency-free host and client entries, so users do not need an install-time build step.
MIT