diff options
Diffstat (limited to 'ep_run/profile_ep.log')
| -rw-r--r-- | ep_run/profile_ep.log | 21 |
1 files changed, 21 insertions, 0 deletions
diff --git a/ep_run/profile_ep.log b/ep_run/profile_ep.log new file mode 100644 index 0000000..d9812a4 --- /dev/null +++ b/ep_run/profile_ep.log @@ -0,0 +1,21 @@ +=== full + component toggles (ms/step, B=24, C512) === +/home/yurenh2/miniconda3/lib/python3.13/site-packages/torch/autograd/graph.py:865: UserWarning: Attempting to run cuBLAS, but there was no current CUDA context! Attempting to set the primary context... (Triggered internally at /pytorch/aten/src/ATen/cuda/CublasHandlePool.cpp:330.) + return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass +FULL ep_step: 7266 + -jacreg: 7242 + -resreg: 7312 + -t1max(no refine): 5886 + t2sel=80: 7384 + t2sel=40: 4485 + plain nudge holo=0 T2=20: 3179 + free relax T1=150 alone: 740 + free relax T1=300 alone: 1480 +=== batch sweep (full) === + B=8: 2353 ms (294.1/sample) + B=24: 7405 ms (308.5/sample) + B=48: 14496 ms (302.0/sample) +=== compile free relax === + free relax T1=150 COMPILED: 507 +=== bf16 full === + full bf16: ERR RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn +DONE |