Commit History
-
Document corrected ERNIE qmm runtime profile
Verified signatureAdds runtime_config.json and corrected explicit quantized-matmul/default allocator metrics. Updates the model card to distinguish serialized config-path measurements from explicit qmm runtime, and documents the PYTORCH_CUDA_ALLOC_CONF allocator pitfall.b292728 -
Enable quantized matmul and refresh PE-off benchmark
Verified signature687a1fe
-
Add files using upload-large-folder tool
Verified signaturef2b7557 -
initial commit
Verified signature1b712d2