Salka Elmadani
ec36668cf5
Better output from the same model. Fused computation, adaptive precision, surgical expert loading. 305 KB, 19 backends, zero dependencies. https://inference-x.com
25 lines
998 B
Bash
Executable File
25 lines
998 B
Bash
Executable File
#!/bin/bash
|
|
# IX-PROFILER PROFILING RUN | Morocco
|
|
# Launch: nohup, runs overnight on VPS
|
|
|
|
CD=${1:-.}
|
|
MODEL=${2:?"Usage: $0 <repo_dir> <model_path>"}
|
|
OUT=${3:-expert_profile.csv}
|
|
LOG=${4:-profile_run.log}
|
|
|
|
echo "[IX] IX profiling started: $(date)" > $LOG
|
|
echo "[IX] Model: $MODEL" >> $LOG
|
|
echo "[IX] Output: $OUT" >> $LOG
|
|
|
|
# Single comprehensive prompt - reasoning + code + analysis
|
|
# 50 tokens output = enough to profile all 60 layers
|
|
$CD/inference-x $MODEL \
|
|
-p "You are a systems architect. Design a distributed edge computing network for low-power AI inference. The system must handle intermittent power sources, variable network connectivity, and heterogeneous hardware. Provide technical specifications for: 1) Node hardware requirements 2) Model distribution strategy 3) Fault tolerance mechanisms 4) Power management. Think step by step." \
|
|
-n 50 \
|
|
-t 0.6 \
|
|
--profile $OUT \
|
|
>> $LOG 2>&1
|
|
|
|
echo "[IX] Profiling completed: $(date)" >> $LOG
|
|
echo "[IX] Profile saved to: $OUT" >> $LOG
|