I hereby claim:
- I am icemelon on github.
- I am haichen (https://keybase.io/haichen) on keybase.
- I have a public key whose fingerprint is 5EC6 0F17 91AA D9CF 6B44 8E63 2B99 E22C 56C2 FCA7
To claim this, I am signing this object:
| Hey, I'm icemelon-2696494 and I have contributed to the RISC Zero STARK-to-SNARK Prover MPC Phase2 Trusted Setup ceremony. | |
| The following are my contribution signatures: | |
| Circuit # 1 (stark_verify) | |
| Contributor # 76 | |
| Contribution Hash: 39b65d41 397b0c08 14bdda53 927ce83a | |
| 017cafe3 62c4b052 3e6dd66d d28e3435 | |
| ad42499c 14d0bf94 24466d8e 7f9a9051 | |
| d322c677 ad126e85 012804ef b0b8f960 |
I hereby claim:
To claim this, I am signing this object:
| model | batch | seq length | MXNet latency (ms) | TVM latency (ms) | speedup |
|---|---|---|---|---|---|
| BERT | 1 | 64 | 26.1 | 12.6 | 2.1 |
| BERT | 1 | 128 | 45.8 | 19.2 | 2.4 |
| BERT | 1 | 256 | 99.4 | 35.3 | 2.8 |
| DistilBERT | 1 | 64 | 13.4 | 6.2 | 2.2 |
| DistilBERT | 1 | 128 | 23.2 | 9.5 | 2.5 |
| DistilBERT | 1 | 256 | 50.1 | 17.5 | 2.9 |
| import time | |
| import argparse | |
| import numpy as np | |
| import mxnet as mx | |
| import gluonnlp as nlp | |
| import tvm | |
| from tvm import relay | |
| import tvm.contrib.graph_runtime as runtime | |
| def timer(thunk, repeat=1, number=10, dryrun=3, min_repeat_ms=1000): |
| import numpy as np | |
| import tvm | |
| from tvm import relay | |
| from tvm.relay.ty import TupleType, TensorType | |
| from tvm.relay.prelude import Prelude | |
| from tvm.runtime.container import ADT | |
| def _get_relay_input_vars(input_shapes, prelude): | |
| def _is_int_seq(seq): |
| for yo in range(128): | |
| for xo in range(128): | |
| C[yo*8:yo*8+8][xo*8:xo*8+8] = 0 | |
| for ko in range(128): | |
| for yi in range(8): | |
| for xi in range(8): | |
| for ki in range(8): | |
| C[yo*8+yi][xo*8+xi] += | |
| A[ko*8+ki][yo*8+yi] * B[ko*8+ki][xo*8+xi] |
| import sys | |
| import numpy | |
| import timeit | |
| import logging | |
| import tvm | |
| from tvm import autotvm | |
| @autotvm.template | |
| def matmul(M, K, N): | |
| A = tvm.placeholder((M, K), name='A') |