Skip to main content

TileRT: Tile-Based Runtime for
Ultra-Low-Latency LLM Inference

GitHub repository PyPI version HuggingFace

TileRT serves large language models (LLMs) in ultra-low-latency scenarios — pushing the latency limits of hundred-billion-parameter models to millisecond-level time per output token (TPOT) without compromising model size or quality. Its tile-level runtime engine decomposes LLM operators into fine-grained tile tasks and dynamically overlaps computation, I/O, and communication across multiple GPUs.

The current preview supports DeepSeek-V3.2 and GLM-5 on 8× NVIDIA B200. For full usage, examples, and news, see the GitHub repository.

GLM-5.1-FP8 token generation with TileRT v0.1.5
GLM-5.1-FP8 token generation speed with TileRT v0.1.5. Output length 1K, input length 1K–192K. Bars compare TileRT without MTP, with MTP at average acceptance length 3.2, and the peak under best-case MTP acceptance.

Installation

The official tilert==0.1.5 wheel on PyPI was compiled against the following stack. Treat these as hard requirements, not lower bounds.

Component Pinned version
NVIDIA driver Supports CUDA 13.2 runtime
Operating System Linux x86_64, glibc ≥ 2.28 (manylinux_2_28)
Python 3.12
PyTorch torch==2.11.0+cu130
transformers 4.46.3
tokenizers 0.20.3

The pinned environment is preinstalled in our official image — the recommended way to run TileRT, avoiding version drift on the host. The image is mirrored to two registries; pull from whichever is reachable:

docker pull ghcr.io/tile-ai/tilert:cu132-latest   # GitHub Container Registry
docker pull tileai/tilert:cu132-latest            # Docker Hub

Launch a container with all 8 GPUs attached, then install the wheel inside:

docker run --rm -it --gpus all --ipc=host \
    -v "$PWD":/workspace -w /workspace \
    ghcr.io/tile-ai/tilert:cu132-latest

# Install from PyPI:
pip install tilert==0.1.5

# Or pin the exact wheel from the GitHub Release page (same artifact,
# useful when PyPI is unreachable):
pip install https://github.com/tile-ai/TileRT/releases/download/v0.1.5/tilert-0.1.5-cp312-cp312-manylinux_2_28_x86_64.whl

Verify the install:

python -c "import tilert, torch; print('tilert', tilert.__version__, '/ torch', torch.__version__, '/ cuda', torch.version.cuda)"
# Expected: tilert 0.1.5 / torch 2.11.0+cu130 / cuda 13.0

Documentation

For weight conversion, the generation CLI, the programmatic API, Multi-Token Prediction (MTP), and the latest benchmarks, see the TileRT GitHub repository.

Metadata

Release files for tilert 0.1.7

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

Built distribution (wheel)

Table of built distributions (wheels) for tilert 0.1.7
File Interpreter ABI Platform Actions
tilert-0.1.7-cp312-cp312-manylinux_2_28_x86_64.whl CPython 3.12 CPython 3.12 Linux glibc 2.28+ x86-64 Details for tilert-0.1.7-cp312-cp312-manylinux_2_28_x86_64.whl

Release files / tilert-0.1.7-cp312-cp312-manylinux_2_28_x86_64.whl

Download URL tilert-0.1.7-cp312-cp312-manylinux_2_28_x86_64.whl
Size 11.8 MB
Tags CPython 3.12 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
d9d7554c7562bc9e840283a01789d301e6f546091058dbde61196ed20b0d1a54
BLAKE2b-256 checksum
How to use checksums
0d362ca7cac2365fd307d94bf3cd4682c48223155c473d767f30da792a4c7dfa
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.13

Security for tilert 0.1.7

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.

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