Skip to main content

Custom Triton/CUDA kernels that complement Liger Kernel for LLM post-training

Project description

Chalk

Custom Triton/CUDA kernels that complement Liger Kernel.

pip install freesolo-chalk

Liger fuses the cross-entropy, activation, and RMSNorm paths. Chalk fills the gaps that matter for Freesolo's Flash post-training stack — fused GEMMs, the LoRA-delta matmuls, the QKV norm+RoPE epilogue, embedding gather, and FP8 frozen-base GEMMs — each behind a documented, benchmarked, opt-in entry point.

Chalk's repository layout and conventions intentionally mirror Liger Kernel.

Layout

src/chalk/
  ops/           # raw Triton/CUDA kernels + autograd.Function wrappers
  transformers/  # model-level installers that monkeypatch kernels into HF modules
  utils.py       # device detection helpers
test/            # correctness + gating tests (mirrors test/ops, test/transformers)

Design principles

  • Worker-side kernel library. Like Liger, chalk depends on torch + triton — it is meant to be installed where kernels actually run (the GPU worker), so consumers should depend on it from a gpu extra rather than their base install. Importing the top-level chalk package is still cheap (kernels lazy-load), so probing chalk.utils.infer_device() never forces a heavy import.
  • Complements, not replaces, Liger. Liger fuses CE / activation / RMSNorm; chalk fuses the GEMMs, LoRA delta, QKV epilogue, embedding, and FP8 base.
  • Safe fallback. Every installer is arch-gated, runs a numeric self-test on install, patches only frozen nn.Linear layers (never trainable / PEFT-wrapped layers), and silently falls back to the eager / Liger path on any import / compile / self-test failure.
  • Opt-in & evidence-based. Kernels are off unless explicitly enabled, and every kept kernel has end-to-end loss-curve evidence — not just a microbenchmark.

Development

pip install -e '.[dev]'
make checkstyle   # ruff check + format
make test         # pytest with coverage

Status

Intentionally minimal to start — kernels are landed one at a time under chalk/ops + chalk/transformers, each with correctness tests.

License

BSD-2-Clause. See LICENSE and NOTICE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

freesolo_chalk-0.4.2.tar.gz (160.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

freesolo_chalk-0.4.2-py3-none-any.whl (104.2 kB view details)

Uploaded Python 3

File details

Details for the file freesolo_chalk-0.4.2.tar.gz.

File metadata

  • Download URL: freesolo_chalk-0.4.2.tar.gz
  • Upload date:
  • Size: 160.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.14 {"installer":{"name":"uv","version":"0.11.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for freesolo_chalk-0.4.2.tar.gz
Algorithm Hash digest
SHA256 defc3f34f48b6c6ab83d51a6365065d6bff476e4e552c07b1530373d14b51f8e
MD5 ec5c22a4834a1d78df95180b7e240330
BLAKE2b-256 c8afe3103d6efd538ed04aad5a2a18012dd2dd0b642111f8e2b567b18c4a56d8

See more details on using hashes here.

File details

Details for the file freesolo_chalk-0.4.2-py3-none-any.whl.

File metadata

  • Download URL: freesolo_chalk-0.4.2-py3-none-any.whl
  • Upload date:
  • Size: 104.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.14 {"installer":{"name":"uv","version":"0.11.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for freesolo_chalk-0.4.2-py3-none-any.whl
Algorithm Hash digest
SHA256 ac9705bc1cb35dad5ef572d725c14c0c2501cd863f7ac7a00f75cc0163053825
MD5 9e9dfcd25d55f58155131f561eb2aa2f
BLAKE2b-256 7ee38be703097ec3d92b1527f5f30c91a729bbc4273a47656fc60841fe8b2123

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page