Open Issues Need Help
View All on GitHub enhancement good first issue measurement
hongping-zh/ecocompute-mlcube hongping-zh/ecocompute-mlcube EcoCompute energy-methodology MLCube: measure LLM inference energy (GPU x model x precision x batch) via NVML, MLCommons-style energy reporting.
Open project →
0
EcoCompute energy-methodology MLCube: measure LLM inference energy (GPU x model x precision x batch) via NVML, MLCommons-style energy reporting.
Python
Add context_length parameter to measurement 8 days ago
enhancement good first issue measurement schema
hongping-zh/ecocompute-mlcube hongping-zh/ecocompute-mlcube EcoCompute energy-methodology MLCube: measure LLM inference energy (GPU x model x precision x batch) via NVML, MLCommons-style energy reporting.
Open project →
0
EcoCompute energy-methodology MLCube: measure LLM inference energy (GPU x model x precision x batch) via NVML, MLCommons-style energy reporting.
Python
Add AMD GPU support detection 9 days ago
enhancement good first issue
hongping-zh/ecocompute-mlcube hongping-zh/ecocompute-mlcube EcoCompute energy-methodology MLCube: measure LLM inference energy (GPU x model x precision x batch) via NVML, MLCommons-style energy reporting.
Open project →
0
EcoCompute energy-methodology MLCube: measure LLM inference energy (GPU x model x precision x batch) via NVML, MLCommons-style energy reporting.
Python
Document how to add a new inference backend 9 days ago
documentation enhancement good first issue
hongping-zh/ecocompute-mlcube hongping-zh/ecocompute-mlcube EcoCompute energy-methodology MLCube: measure LLM inference energy (GPU x model x precision x batch) via NVML, MLCommons-style energy reporting.
Open project →
0
EcoCompute energy-methodology MLCube: measure LLM inference energy (GPU x model x precision x batch) via NVML, MLCommons-style energy reporting.
Python
Add batch_size > 1 support to entrypoint 9 days ago
enhancement good first issue measurement
hongping-zh/ecocompute-mlcube hongping-zh/ecocompute-mlcube EcoCompute energy-methodology MLCube: measure LLM inference energy (GPU x model x precision x batch) via NVML, MLCommons-style energy reporting.
Open project →
0
EcoCompute energy-methodology MLCube: measure LLM inference energy (GPU x model x precision x batch) via NVML, MLCommons-style energy reporting.
Python