Instructions to use SuperexponentialAI/relu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use SuperexponentialAI/relu with Kernels:
# !pip install kernels from kernels import get_kernel # a version (or an explicit revision) is required; see the "Files and versions" tab for the available ones kernel = get_kernel("SuperexponentialAI/relu", version=1) - Notebooks
- Google Colab
- Kaggle
Add benchmarks/ for the official CLI harness; README harness notes (MK, powered by Claude)
Browse files- README.md +18 -2
- benchmarks/benchmark.py +102 -0
README.md
CHANGED
|
@@ -141,8 +141,24 @@ fp16/bf16 creation bug on this GPU).
|
|
| 141 |
|
| 142 |
## Benchmarks
|
| 143 |
|
| 144 |
-
|
| 145 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
|
| 147 |
Full methodology and results: see `OPTIMIZATION.md`, `DTYPE_THROUGHPUT.md`,
|
| 148 |
and `INVESTIGATION_L2.md` in this repository.
|
|
|
|
| 141 |
|
| 142 |
## Benchmarks
|
| 143 |
|
| 144 |
+
Official-harness scripts live in `benchmarks/`: `ReluBenchmark` mirrors
|
| 145 |
+
upstream's fp32 base/large workloads (directly comparable), and
|
| 146 |
+
`ReluDtypeBenchmark` adds the fp16/bf16/int8 workloads upstream lacks.
|
| 147 |
+
|
| 148 |
+
- Local checkout: `kernels benchmark ./relu-build` (all workloads verify
|
| 149 |
+
against `F.relu`).
|
| 150 |
+
- Remote (`kernels benchmark SuperexponentialAI/relu --version 2`)
|
| 151 |
+
requires this repo to be hosted as a `kernel`-type repo; it is
|
| 152 |
+
currently `model`-type (kernel-repo creation is restricted for this
|
| 153 |
+
account), so use the local form until it migrates. The same caveat
|
| 154 |
+
applies to the `get_kernel` snippet above — load via
|
| 155 |
+
`snapshot_download` + `sys.path` in the meantime.
|
| 156 |
+
|
| 157 |
+
The harness times host-side wall clock per iteration; on boost-clocked
|
| 158 |
+
GPUs at L2-resident sizes this understates the kernel's true speedup
|
| 159 |
+
relative to the single-shot reference timing. The nsys
|
| 160 |
+
GPU-kernel-duration numbers above are the trustworthy comparison
|
| 161 |
+
(`INVESTIGATION_L2.md` explains the mechanism).
|
| 162 |
|
| 163 |
Full methodology and results: see `OPTIMIZATION.md`, `DTYPE_THROUGHPUT.md`,
|
| 164 |
and `INVESTIGATION_L2.md` in this repository.
|
benchmarks/benchmark.py
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
import torch.nn.functional as F
|
| 3 |
+
|
| 4 |
+
from kernels.benchmark import Benchmark
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
class ReluBenchmark(Benchmark):
|
| 8 |
+
"""Same workloads/names as upstream kernels-community/relu (fp32
|
| 9 |
+
base/large) so results are directly comparable across the two repos."""
|
| 10 |
+
|
| 11 |
+
seed: int = 42
|
| 12 |
+
|
| 13 |
+
def setup(self):
|
| 14 |
+
self.x = torch.randn(1024, 1024, device=self.device, dtype=torch.float32)
|
| 15 |
+
self.out = torch.empty_like(self.x)
|
| 16 |
+
|
| 17 |
+
def benchmark_base(self):
|
| 18 |
+
self.out = self.kernel.relu(self.x)
|
| 19 |
+
|
| 20 |
+
def verify_base(self) -> torch.Tensor:
|
| 21 |
+
return F.relu(self.x)
|
| 22 |
+
|
| 23 |
+
def setup_large(self):
|
| 24 |
+
self.x = torch.randn(4096, 4096, device=self.device, dtype=torch.float32)
|
| 25 |
+
self.out = torch.empty_like(self.x)
|
| 26 |
+
|
| 27 |
+
def benchmark_large(self):
|
| 28 |
+
self.out = self.kernel.relu(self.x)
|
| 29 |
+
|
| 30 |
+
def verify_large(self) -> torch.Tensor:
|
| 31 |
+
return F.relu(self.x)
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
class ReluDtypeBenchmark(Benchmark):
|
| 35 |
+
"""Dtypes this build ships beyond upstream's fp32-only: fp16, bf16, int8.
|
| 36 |
+
base = 1024^2, large = 4096^2, matching ReluBenchmark's shapes."""
|
| 37 |
+
|
| 38 |
+
seed: int = 42
|
| 39 |
+
|
| 40 |
+
def _float_setup(self, side, dtype):
|
| 41 |
+
self.x = torch.randn(side, side, device=self.device, dtype=dtype)
|
| 42 |
+
self.out = torch.empty_like(self.x)
|
| 43 |
+
|
| 44 |
+
def setup_fp16_base(self):
|
| 45 |
+
self._float_setup(1024, torch.float16)
|
| 46 |
+
|
| 47 |
+
def setup_fp16_large(self):
|
| 48 |
+
self._float_setup(4096, torch.float16)
|
| 49 |
+
|
| 50 |
+
def setup_bf16_base(self):
|
| 51 |
+
self._float_setup(1024, torch.bfloat16)
|
| 52 |
+
|
| 53 |
+
def setup_bf16_large(self):
|
| 54 |
+
self._float_setup(4096, torch.bfloat16)
|
| 55 |
+
|
| 56 |
+
def _int8_setup(self, side):
|
| 57 |
+
self.x = torch.randint(
|
| 58 |
+
-128, 128, (side, side), device=self.device, dtype=torch.int8
|
| 59 |
+
)
|
| 60 |
+
self.out = torch.empty_like(self.x)
|
| 61 |
+
|
| 62 |
+
def setup_int8_base(self):
|
| 63 |
+
self._int8_setup(1024)
|
| 64 |
+
|
| 65 |
+
def setup_int8_large(self):
|
| 66 |
+
self._int8_setup(4096)
|
| 67 |
+
|
| 68 |
+
def benchmark_fp16_base(self):
|
| 69 |
+
self.out = self.kernel.relu(self.x)
|
| 70 |
+
|
| 71 |
+
def benchmark_fp16_large(self):
|
| 72 |
+
self.out = self.kernel.relu(self.x)
|
| 73 |
+
|
| 74 |
+
def benchmark_bf16_base(self):
|
| 75 |
+
self.out = self.kernel.relu(self.x)
|
| 76 |
+
|
| 77 |
+
def benchmark_bf16_large(self):
|
| 78 |
+
self.out = self.kernel.relu(self.x)
|
| 79 |
+
|
| 80 |
+
def benchmark_int8_base(self):
|
| 81 |
+
self.out = self.kernel.relu(self.x)
|
| 82 |
+
|
| 83 |
+
def benchmark_int8_large(self):
|
| 84 |
+
self.out = self.kernel.relu(self.x)
|
| 85 |
+
|
| 86 |
+
def verify_fp16_base(self) -> torch.Tensor:
|
| 87 |
+
return F.relu(self.x)
|
| 88 |
+
|
| 89 |
+
def verify_fp16_large(self) -> torch.Tensor:
|
| 90 |
+
return F.relu(self.x)
|
| 91 |
+
|
| 92 |
+
def verify_bf16_base(self) -> torch.Tensor:
|
| 93 |
+
return F.relu(self.x)
|
| 94 |
+
|
| 95 |
+
def verify_bf16_large(self) -> torch.Tensor:
|
| 96 |
+
return F.relu(self.x)
|
| 97 |
+
|
| 98 |
+
def verify_int8_base(self) -> torch.Tensor:
|
| 99 |
+
return F.relu(self.x)
|
| 100 |
+
|
| 101 |
+
def verify_int8_large(self) -> torch.Tensor:
|
| 102 |
+
return F.relu(self.x)
|