dennii/Hermes-Ollama_Models
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add scalable CPU and GPU telemetry

Browse Source
This commit is contained in:
Hermes Agent
2026-08-26 00:11:11 +10:00
parent e858f7a979
commit 2e47e0eae8
6 changed files with 84 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
dashboard/dist/index.js
Vendored
+8 -3
View File
@@ -167,16 +167,21 @@
function RuntimePanel(props) {
var runtime = props.runtime || {}, total = Number(runtime.memory_total_bytes || 0), used = Number(runtime.memory_used_bytes || 0), pct = total ? Math.min(100, used * 100 / total) : 0;
var gpu = runtime.gpu || {}, models = runtime.model_memory || [], loading = runtime.model_loading || [];
var gpu = runtime.gpu || {}, cpu = runtime.cpu || {}, models = runtime.model_memory || [], loading = runtime.model_loading || [], cores = cpu.cores || [], gpus = gpu.gpus || [];
var ollamaBytes = Number(runtime.ollama_model_bytes || 0), ollamaTargetBytes = Number(runtime.ollama_target_model_bytes || ollamaBytes), ollamaPct = total ? Math.min(100, ollamaTargetBytes * 100 / total) : 0;
function percent(value) { return value == null ? "n/a" : Number(value).toFixed(1) + "%"; }
function meter(value) { return value == null ? 0 : Math.max(0, Math.min(100, Number(value))); }
return h("section", { className: "ollama-runtime-panel" },
h("div", { className: "ollama-runtime-heading" }, h("div", null, h("h3", null, "Live runtime memory"), h("p", null, "Updates every second while this panel is open.")), h(Badge, { tone: loading.length ? "live" : (gpu.detected ? "live" : "muted") }, loading.length ? "MODEL LOADING" : (gpu.detected ? "GPU detected" : "CPU-only / no supported GPU telemetry"))),
h("div", { className: "ollama-runtime-heading" }, h("div", null, h("h3", null, "Live runtime memory and hardware"), h("p", null, "Updates every second while this panel is open. Multiple CPUs and GPUs expand into individual cards.")), h(Badge, { tone: loading.length ? "live" : (gpu.detected ? "live" : "muted") }, loading.length ? "MODEL LOADING" : (gpu.detected ? "GPU detected" : "CPU telemetry"))),
h("div", { className: "ollama-runtime-grid" },
h("div", { className: "ollama-runtime-stat" }, h("small", null, "System RAM used"), h("strong", null, fmtBytes(used), " / ", fmtBytes(total)), h("div", { className: "ollama-meter" }, h("span", { style: { width: pct + "%" } })), h("small", null, fmtBytes(runtime.memory_available_bytes || 0), " available")),
h("div", { className: "ollama-runtime-stat ollama-cpu-stat" }, h("small", null, "CPU usage"), h("strong", null, percent(cpu.usage_percent)), h("div", { className: "ollama-meter" }, h("span", { style: { width: meter(cpu.usage_percent) + "%" } })), h("small", null, cpu.count ? cpu.count + " logical CPUs · load " + (cpu.load_average || []).map(function (value) { return Number(value).toFixed(2); }).join(" / ") : "Unavailable")),
h("div", { className: "ollama-runtime-stat" }, h("small", null, "Swap used"), h("strong", null, fmtBytes(runtime.swap_used_bytes || 0), " / ", fmtBytes(runtime.swap_total_bytes || 0)), h("small", null, "Host-wide live statistic")),
h("div", { className: "ollama-runtime-stat" }, h("small", null, "GPU telemetry"), h("strong", null, gpu.telemetry_available ? (gpu.gpus || []).map(function (item) { return item.name + " · " + fmtBytes(item.used_bytes) + " / " + fmtBytes(item.total_bytes); }).join("; ") : "Unavailable"), h("small", null, gpu.detected ? "Ollama VRAM split is still shown below." : "No supported GPU was detected.")),
h("div", { className: "ollama-runtime-stat ollama-gpu-stat" }, h("small", null, "GPU usage"), h("strong", null, percent(gpu.utilization_percent), " · ", gpu.count || 0, " GPU", (gpu.count || 0) === 1 ? "" : "s"), h("div", { className: "ollama-meter" }, h("span", { style: { width: meter(gpu.utilization_percent) + "%" } })), h("small", null, gpu.telemetry_available && gpus.length ? gpus.map(function (item) { return item.name + " · " + fmtBytes(item.used_bytes) + " / " + fmtBytes(item.total_bytes); }).join("; ") : "Unavailable")),
h("div", { className: "ollama-runtime-stat ollama-weight-stat" }, h("small", null, "Ollama model weights"), h("strong", null, fmtBytes(ollamaBytes), " resident"), h("div", { className: "ollama-meter" }, h("span", { style: { width: ollamaPct + "%" } })), h("small", null, loading.length ? "Loading target: " + fmtBytes(ollamaTargetBytes) : "Mapped weight bytes; Linux may report them as file cache"))
),
cores.length > 1 && h("div", { className: "ollama-device-section" }, h("div", { className: "ollama-device-heading" }, h("h4", null, "CPU cores · ", cores.length), h("small", null, "Per-core usage")), h("div", { className: "ollama-device-grid" }, cores.map(function (core) { return h("div", { className: "ollama-device-card", key: core.name }, h("strong", null, core.name.toUpperCase()), h("span", null, percent(core.usage_percent)), h("div", { className: "ollama-meter" }, h("span", { style: { width: meter(core.usage_percent) + "%" } }))); }))),
gpus.length > 1 && h("div", { className: "ollama-device-section" }, h("div", { className: "ollama-device-heading" }, h("h4", null, "GPUs · ", gpus.length), h("small", null, "Per-GPU telemetry")), h("div", { className: "ollama-device-grid" }, gpus.map(function (item) { return h("div", { className: "ollama-device-card ollama-gpu-device-card", key: item.index }, h("strong", null, "GPU ", item.index, " · ", item.name), h("span", null, "Usage ", percent(item.utilization_percent)), h("div", { className: "ollama-meter" }, h("span", { style: { width: meter(item.utilization_percent) + "%" } })), h("small", null, "VRAM ", fmtBytes(item.used_bytes), " / ", fmtBytes(item.total_bytes), " · Free ", fmtBytes(item.free_bytes)), h("small", null, item.temperature_c == null ? "Temperature n/a" : "Temperature " + item.temperature_c.toFixed(0) + "°C", " · ", item.power_watts == null ? "Power n/a" : "Power " + item.power_watts.toFixed(0) + " W")); }))),
h("div", { className: "ollama-memory-chart" + (loading.length ? " loading" : ""), role: loading.length ? "status" : undefined, "aria-live": loading.length ? "polite" : undefined }, loading.length ? h("div", { className: "ollama-loading-progress" }, h("strong", null, "Loading into Ollama memory"), h("span", null, loading.map(function (item) { return item.name; }).join(", ")), h("small", null, loading.map(function (item) { return item.stage + " · " + fmtElapsed(item.elapsed); }).join(" · ")), h("div", { className: "ollama-loading-track" }, h("span", null))) : (props.samples || []).map(function (sample, index) { var height = sample.total ? Math.max(3, Math.min(100, sample.used * 100 / sample.total)) : 3; return h("span", { key: index, title: fmtBytes(sample.used) + " used", style: { height: height + "%" } }); })),
h("div", { className: "ollama-loaded-memory" }, h("h4", null, "Loaded models and capabilities"), models.length ? models.map(function (model) { return h("div", { className: "ollama-loaded-row", key: model.name }, h("strong", null, model.name), h("span", null, "Total ", fmtBytes(model.total_bytes)), h("span", null, "GPU VRAM ", fmtBytes(model.gpu_bytes)), h("span", null, "Normal RAM ", fmtBytes(model.ram_bytes)), h("span", null, model.gpu_offload_percent + "% GPU offload"), h("span", { className: "ollama-loaded-capabilities" }, "Capabilities: ", (model.capabilities || []).join(", ") || "Unknown", " · Input: ", (model.input_modalities || []).join(", ") || "Text", " · ", model.parameter_size || "unknown", " · ", model.quantization || "unknown", " · Context ", model.context_length || "unknown"), h("span", { className: "ollama-permanent-label" }, model.permanent ? "Permanent keep-alive" : "Runtime-loaded")); }) : loading.length ? h("p", null, "Ollama is loading the selected model. Resident memory will appear here when the runner finishes starting.") : h("p", null, "No model is currently loaded. Use the model pool below to load one or more permanently."))
);