MarkBase Admin
ac75faa0cc
CI / build-and-test (push) Has been cancelled
- E4B-MarkBase model (42 layers, 4.4GB) loaded successfully - All Phase 1-6 tests passed (model loading, forward pass, vision/audio towers, token generation, performance) - All stress tests passed (5/5 in 127.6s) - Concurrent inference - Memory stress (67.5 tok/s, 0 NaN) - Continuous generation - Batch processing - Long-running stability - Swift Metal inference engine with multimodal support
14 lines
287 B
Bash
Executable File
14 lines
287 B
Bash
Executable File
#!/bin/bash
|
|
# MarkBaseServer startup script
|
|
|
|
MODEL_DIR="./models/E4B-MarkBase"
|
|
PORT=8080
|
|
MODEL_ID="gemma-4-e4b-markbase"
|
|
|
|
echo "Starting MarkBaseServer..."
|
|
echo " Model: $MODEL_ID"
|
|
echo " Port: $PORT"
|
|
|
|
cd ~/MarkBaseEngine
|
|
.build/release/MarkBaseServer "$MODEL_DIR" "$PORT" "$MODEL_ID"
|