mbolt
Profile-guided layout optimization for GGUF MoE models — BOLT/PGO, but for weights.
Trace which experts your workload co-activates, rewrite the GGUF so those bytes sit together on disk, decode with explicit-read prefetch: 1.55–1.63× faster memory-squeezed MoE streaming in llama.cpp, 2.23× at the storage level. Weights byte-exact, +0.003% size.
pip install mbolt
mbolt-sim cluster route.bin -o perms.json # co-activation -> permutations
mbolt model.gguf perms.json -o model.opt.gguf --layout interleave
mbolt-sim gate model.gguf route.bin perms.json -o gate.json # predict before rewriting
Trace capture and the explicit-read prefetcher need a small llama.cpp patch
(MBOLT_TRACE / MBOLT_PREFETCH env vars) shipped in the repo.
Full docs, benchmark reports, and the llama.cpp patch: https://github.com/doramirdor/mbolt
MIT license.
1 maintainer
Metadata
1 maintainer
Release files for mbolt 0.1.0
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 | |
|---|---|---|---|---|
| mbolt-0.1.0.tar.gz | 40.0 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mbolt-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 60.0 kB
Release files / mbolt-0.1.0.tar.gz
| Download URL | mbolt-0.1.0.tar.gz |
|---|---|
| Size | 40.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9558d278444f1b2dabef3727b95f4a5ce9281b33bb9cde180ed75c507672542d
|
|
BLAKE2b-256 checksum How to use checksums |
656ad33bd3166bbeb154d2278f06d69683152988515018b7a4843e311540a82d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.20 {"installer":{"name":"uv","version":"0.11.20","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 / mbolt-0.1.0-py3-none-any.whl
| Download URL | mbolt-0.1.0-py3-none-any.whl |
|---|---|
| Size | 20.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4f3466146e98ebf0793cd379912a0796d02a63b77cb3dacb8b5d754db6477be7
|
|
BLAKE2b-256 checksum How to use checksums |
70df76aa073f3bf7ac853a8a87ab5142ba4eb48a5bfadff9e31fa162cfbd2e27
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.20 {"installer":{"name":"uv","version":"0.11.20","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 mbolt 0.1.0
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.
