ur-grue/toptop

Apple Silicon support: GPU utilization + unified-memory pressure on macOS about 3 hours ago

enhancement help wanted

0

The local-inference observability layer for your terminal: live tokens/sec, VRAM-spill & throttle warnings, the GPU metrics nvidia-smi can't show. Also a gorgeous htop/btop-class system monitor. Rust, zero deps.

Rust

#btop#gpu-monitoring#htop#inference#llama-cpp#llm#llmops#nvidia#observability#ollama#prometheus#ratatui#rust#system-monitor#tokens-per-second#tui#vllm#vram

Packaging: crates.io, AUR, nixpkgs, Homebrew tap about 4 hours ago

help wanted packaging

ur-grue/toptop

0

The local-inference observability layer for your terminal: live tokens/sec, VRAM-spill & throttle warnings, the GPU metrics nvidia-smi can't show. Also a gorgeous htop/btop-class system monitor. Rust, zero deps.

Rust

#btop#gpu-monitoring#htop#inference#llama-cpp#llm#llmops#nvidia#observability#ollama#prometheus#ratatui#rust#system-monitor#tokens-per-second#tui#vllm#vram

Ship a ready-made Grafana dashboard for --serve-metrics about 5 hours ago

enhancement help wanted

ur-grue/toptop

0

The local-inference observability layer for your terminal: live tokens/sec, VRAM-spill & throttle warnings, the GPU metrics nvidia-smi can't show. Also a gorgeous htop/btop-class system monitor. Rust, zero deps.

Rust

#btop#gpu-monitoring#htop#inference#llama-cpp#llm#llmops#nvidia#observability#ollama#prometheus#ratatui#rust#system-monitor#tokens-per-second#tui#vllm#vram

Make alert thresholds configurable (config.conf + CLI) about 5 hours ago

enhancement good first issue

ur-grue/toptop

0

The local-inference observability layer for your terminal: live tokens/sec, VRAM-spill & throttle warnings, the GPU metrics nvidia-smi can't show. Also a gorgeous htop/btop-class system monitor. Rust, zero deps.

Rust

#btop#gpu-monitoring#htop#inference#llama-cpp#llm#llmops#nvidia#observability#ollama#prometheus#ratatui#rust#system-monitor#tokens-per-second#tui#vllm#vram

Detect more inference runtimes (TensorRT-LLM, MLC, llamafile /metrics, LM Studio API) about 5 hours ago

enhancement help wanted good first issue

ur-grue/toptop

0

The local-inference observability layer for your terminal: live tokens/sec, VRAM-spill & throttle warnings, the GPU metrics nvidia-smi can't show. Also a gorgeous htop/btop-class system monitor. Rust, zero deps.

Rust

#btop#gpu-monitoring#htop#inference#llama-cpp#llm#llmops#nvidia#observability#ollama#prometheus#ratatui#rust#system-monitor#tokens-per-second#tui#vllm#vram

Open Issues Need Help