Flash Hog
This repo contains the code for Flash Higher-Order-Gradients, aka. Flash Hog. This kernel achieves around a 3.7x speedup over an XLA optimized kernel, with linear memory scaling instead of quadratic scaling.
Installation
uv add flash-hog
Method
Flash Hog does 4 recomputation passes to avoid any atomics or saving any intermediary tensors of shape (N_Q, N_K).
This shakes out to be thread-wise tiling across Q in 3 passes first, once to compute dd, then once for b, then once for both dQ' and ddO.
Finally we do another pass tiled over K, producing dK' and dV'.
The equations we implement are the following:
1 maintainer
Metadata
1 maintainer
Release files for flash-hog 0.6.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| flash_hog-0.6.0.tar.gz | 20.8 kB | Without provenance | Details for flash_hog-0.6.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| flash_hog-0.6.0-py3-none-any.whl | Python 3 | none | any | Details for flash_hog-0.6.0-py3-none-any.whl |
Total release size: 48.6 kB
Release files / flash_hog-0.6.0.tar.gz
| Download URL | flash_hog-0.6.0.tar.gz |
|---|---|
| Size | 20.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
23641f16935f1b7aa04d62ed6a82c2b9b40ea5497d0c5201e5072ae31d32960c
|
|
BLAKE2b-256 checksum How to use checksums |
13ac1c1c34491a0e5b5284413a587a030c5c80e2846878d71c168572718fb8b0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.21 {"installer":{"name":"uv","version":"0.11.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / flash_hog-0.6.0-py3-none-any.whl
| Download URL | flash_hog-0.6.0-py3-none-any.whl |
|---|---|
| Size | 27.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
760acea57d630edb8412f5fabf295b5fcd0e2cfdcfe9002430e3c8fd7b643cf7
|
|
BLAKE2b-256 checksum How to use checksums |
3a3f98d5f450dc17b0abd5a219634f4de440176287bac6eb13c6d8a65790d0a9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.21 {"installer":{"name":"uv","version":"0.11.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for flash-hog 0.6.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
