Skip to main content

tyle

TYLE (Tiled Inference Layout Encoding): a CPU-native, single-file model format for local LLM inference. Spec: https://csp.gitbook.io/genai/foss/tile

Status

Basic container implemented per spec v0.2 draft:

  • 64-byte header with flags, magic TYLE, little-endian

  • GGUF-style KV metadata block (all value types, arrays of scalars/strings)

  • Tensor directory with encoding, quant bits, tile layout, exec order, GPU offload score

  • Optional schedule hints block and NUMA shard map

  • Page-aligned tensor data, ordered by exec_order_index when FLAG_EXEC_ORDER is set

  • Reader returns zero-copy numpy views over an mmap

  • LUT packing (spec §4.3): tyle.pack_lut_weights is a port of T-MAC preprocess_weights. tyle.make_lut_tensors builds the <name> (LUT indices) and <name>.scales tensors with the tuning parameters stored as lut.*. tyle.lut_view reshapes a loaded tensor to the kernel layout and rejects a tuning mismatch.

Not implemented yet: kernels, AMX packing (payloads are stored as given), sparsity block. Per-tensor parameters (e.g. lut.bits, amx.source_quant) go in Tensor.extras and are stored in the metadata block as tensor.<name>.<key>.

Usage

import numpy as np
import tyle
from tyle import constants as C

tf = tyle.TyleFile(
    metadata={
        "tyle.arch": "llama",
        "tyle.name": "demo",
        "tyle.context_length": tyle.Typed(C.VT_U32, 2048),
        "tyle.embedding_length": tyle.Typed(C.VT_U32, 64),
        "tyle.block_count": tyle.Typed(C.VT_U32, 2),
        "tyle.head_count": tyle.Typed(C.VT_U32, 4),
        "tyle.head_count_kv": tyle.Typed(C.VT_U32, 4),
        "tyle.target_isa": ["avx512_vnni"],
        "tyle.tokenizer.model": "bpe",
        "tyle.tokenizer.tokens": ["a", "b"],
    },
    tensors=[tyle.Tensor("w", (4, 4), np.zeros((4, 4), np.float32))],
)
tyle.write(tf, "demo.tyle")
print(tyle.load("demo.tyle").tensor("w").data.shape)

LUT tensors

# w: uint8 (M, K), values already biased by 2**(bits-1); scales/zeros: (M, K // group_size)
params = tyle.LutParams(bits=2)  # g=4, bm=512, kfactor=16, simd_n_in=16, simd_n_out=8
tensors = tyle.make_lut_tensors("blk.0.attn_q", w, scales, zeros, params)
# ... tyle.write(tyle.TyleFile(metadata, tensors), "model.tyle")
packed = tyle.lut_view(tyle.load("model.tyle").tensor("blk.0.attn_q"), expected=params)

Shapes must satisfy: K % g == 0, (K//g) % kfactor == 0, (M*bits) % bm == 0. The packed layout is only valid for the tuning it was built with.

Install

/opt/miniconda3/envs/test12/bin/pip install -r requirements.txt

Metadata

Release files for tyle 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for tyle 0.1.0
File Size Uploaded Provenance Actions
tyle-0.1.0.tar.gz 11.1 kB Without provenance Details for tyle-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for tyle 0.1.0
File Interpreter ABI Platform Actions
tyle-0.1.0-py3-none-any.whl Python 3 none any Details for tyle-0.1.0-py3-none-any.whl

Total release size: 23.2 kB

Release files / tyle-0.1.0.tar.gz

Download URL tyle-0.1.0.tar.gz
Size 11.1 kB
Tags Source
SHA-256 checksum
How to use checksums
aee27b5d4df5f2707103c31d807815e7079391e3e48d664e470eeae03e242591
BLAKE2b-256 checksum
How to use checksums
50b7794bff1401fa41faeb64efe87a04a148d21c6f2f9fbbcd47b802dd394219
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.12

Release files / tyle-0.1.0-py3-none-any.whl

Download URL tyle-0.1.0-py3-none-any.whl
Size 12.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
cc63df9883ad2b0128fda55977defab60d155064014bf3bb68486cc3f3458365
BLAKE2b-256 checksum
How to use checksums
32487084952fed8a0dbeadbf210abb8e10da6d7f4efd79b5f4c05ee113dcccc1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.12

Security for tyle 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.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page