Open Issues Need Help
View All on GitHub [Research] Empirical study: quantized LLM runtime characteristics under resource pressure about 1 month ago
enhancement good first issue research
assassinaj602/edgepulse assassinaj602/edgepulse 🔬 Runtime observability framework for on-device AI — trace memory, latency, thermal state and battery draw during inference
Open project →
0
🔬 Runtime observability framework for on-device AI — trace memory, latency, thermal state and battery draw during inference
#ai-reliability#dart#developer-tools#edge-ai#edge-computing#fault-injection#flutter#gguf#llm#memory-profiling#mobile-ai#observability#on-device-ai#onnx#performance-profiling#quantization#runtime-observability#tensorflow-lite#thermal-monitoring#tinyml
[CI] GitHub Actions — test, analyze, and coverage for all packages about 1 month ago
enhancement good first issue performance
assassinaj602/edgepulse assassinaj602/edgepulse 🔬 Runtime observability framework for on-device AI — trace memory, latency, thermal state and battery draw during inference
Open project →
0
🔬 Runtime observability framework for on-device AI — trace memory, latency, thermal state and battery draw during inference
#ai-reliability#dart#developer-tools#edge-ai#edge-computing#fault-injection#flutter#gguf#llm#memory-profiling#mobile-ai#observability#on-device-ai#onnx#performance-profiling#quantization#runtime-observability#tensorflow-lite#thermal-monitoring#tinyml
[Core] JSON, Markdown, and CSV exporters for InferenceTrace about 1 month ago
enhancement good first issue core exporter
assassinaj602/edgepulse assassinaj602/edgepulse 🔬 Runtime observability framework for on-device AI — trace memory, latency, thermal state and battery draw during inference
Open project →
0
🔬 Runtime observability framework for on-device AI — trace memory, latency, thermal state and battery draw during inference
#ai-reliability#dart#developer-tools#edge-ai#edge-computing#fault-injection#flutter#gguf#llm#memory-profiling#mobile-ai#observability#on-device-ai#onnx#performance-profiling#quantization#runtime-observability#tensorflow-lite#thermal-monitoring#tinyml