ImportBot: Import: llm-visuals, @trustinter; repos DingoOz/llm-visuals

2026-10-30T08:38:27Z

Import: llm-visuals, @trustinter; repos DingoOz/llm-visuals

← Older revision		Revision as of 08:38, 30 October 2026
Line 1:		Line 1:
			{{DISPLAYTITLE:llm-visuals}}
	{{Status\|Reported}} {{Cards\|both}}		{{Status\|Reported}} {{Cards\|both}}

ImportBot: Import: llm-visuals, @trustinter; repos DingoOz/llm-visuals

2026-10-30T08:04:42Z

Import: llm-visuals, @trustinter; repos DingoOz/llm-visuals

New page

{{Status|Reported}} {{Cards|both}}

'''llm-visuals''' is a live terminal dashboard for a local inference server. It auto-detects llama-server, ollama, vLLM, SGLang and several other engines and shows decode and prefill speed, time to first token, per-GPU utilisation, power, HBM temperature, clock-throttle reasons and the VRAM split between weights and KV cache. Not CMP-specific, but its author verified the HBM temperature readout on a CMP 170HX. Author: GitHub DingoOz, MIT, Rust. Repository: https://github.com/DingoOz/llm-visuals {{Source|handle=trustinter|date=2026-10-17|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1561025692890832906}}<br />{{Source|handle=trustinter|date=2026-10-17|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1561025692890832906|repo=https://github.com/DingoOz/llm-visuals}}.

== Install and run ==
Prebuilt binaries for Linux, Windows and macOS (x86-64 and ARM64) are on the GitHub releases page. From source, with Rust 1.75 or newer:
<syntaxhighlight lang="bash">
git clone https://github.com/DingoOz/llm-visuals && cd llm-visuals
cargo run --release -- --demo # no server needed
cargo run --release # auto-detects the local server
</syntaxhighlight>
{{Source|handle=trustinter|date=2026-10-17|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1561025692890832906|repo=https://github.com/DingoOz/llm-visuals}}.

== What it shows that matters on a 170HX ==
* '''HBM temperature''' through NVML field value 82 (<code><nowiki>temperature.memory</nowiki></code> on the nvidia-smi fallback), next to the die temperature. It raises a "memory hot" alert when the HBM stays at or above the driver's memory max-operating temperature (95 C if the driver names none) for 3 seconds. Thresholds people use are on [[Monitoring]].
* '''Throttle reasons''' as badges: THERM (hardware thermal), BRAKE (hardware power brake, an external signal such as PWRBRK#), HW, PWR (software power cap), SYNC, APP.
* '''Energy''': total board power over all cards, tokens per joule, Wh per 1,000 tokens.
* '''vLLM''' through its standard <code><nowiki>/metrics</nowiki></code>, which the community's vLLM forks keep: decode, prefill without cached prompt tokens, prefix-cache hit rate, and the VRAM split from the served model and the server's command line.
{{Source|handle=trustinter|date=2026-10-17|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1561025692890832906|repo=https://github.com/DingoOz/llm-visuals}}.

== Caveats ==
* A general dashboard; the 170HX appears only as the card the memory temperature path was verified on.
* MoE expert routing needs a llama.cpp patch shipped in the repository; without it the expert view is a visual stand-in.
* Very active; note the version when you report numbers from it.
{{Source|handle=trustinter|date=2026-10-17|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1561025692890832906|repo=https://github.com/DingoOz/llm-visuals}}.

== See also ==
* [[Monitoring]]
* [[Tools]]

{{ImportFooter}}
[[Category:Tools]]
[[Category:8 GB]]
[[Category:10 GB]]

Llm-visuals - Revision history

ImportBot: Import: llm-visuals, @trustinter; repos DingoOz/llm-visuals

ImportBot: Import: llm-visuals, @trustinter; repos DingoOz/llm-visuals