In the Crest catalog
lightseekorg/tokenspeed
TokenSpeed is a speed-of-light LLM inference engine.
- Stars
- 2.2K
- Forks
- 301
- Language
- Python
- Last push
- 22d ago
- Last release
- 3mo ago
Linked by the package’s own registry metadata.GitHub (opens in a new tab)
Package · PyPI
tokenspeed
PyPI · v0.1.1 · MIT License
TokenSpeed is a speed-of-light LLM inference engine.
Tentative categories were assigned with moderate confidence (0.5 to 0.75): they are shown, but they do not count toward a category’s momentum. How categories work
Install
pip install tokenspeedAdoption
- Adoption
- Not published by PyPI
- Not published
- Popularity
- Not published by PyPI
- Not published
- Dependents
- Not published by PyPI
- Not published
- Maintenance
- 0.91
- DerivedRelease cadence and recency, 0 to 1
- Releases per year
- 9.8
- 2 versions over its life
Growth by period
PyPI publishes no adoption figure, so there is no growth to derive. Nothing is estimated in its place.
- 7 days
- Not published by PyPI
- Not published
- 30 days
- Not published by PyPI
- Not published
- 90 days
- Not published by PyPI
- Not published
- 1 year
- Not published by PyPI
- Not published
Adoption history
Adoption history
PyPI publishes no adoption count, so there is no history to chart. That is a fact about the registry, not a gap in ours: the package’s releases and maintenance are measured instead.
Facts from the registry
- Latest version
- v0.1.1
- 2 versions
- First published
- JUL 24, 2026
- Last release
- OCT 6, 2026
- 18d ago
- Licence
- MIT License
Repository
Dependencies latest version · v0.1.1
Runtime 48
- aiohttpAny version
- compressed-tensorsAny version
- dillAny version
- einopsAny version
- fastapiAny version
- grpcio-health-checking
==1.81.1 - grpcio-reflection
==1.81.1 - hf_transferAny version
- huggingface_hubAny version
- modelscopeAny version
- msgspecAny version
- ninjaAny version
- numpyAny version
- openai
>=2.24.1 - openai-harmonyAny version
- orjsonAny version
- packagingAny version
- partial-json-parserAny version
- peftAny version
- pillowAny version
- prometheus-clientAny version
- psutilAny version
- py-spyAny version
- pybase64Any version
- pybind11Any version
- pydanticAny version
- pytest-asyncioAny version
- python-multipartAny version
- pyzmqAny version
- requestsAny version
- setproctitleAny version
- tiktokenAny version
- tokenspeed-kernel
>=0.1.4 - tokenspeed-mooncake
>=0.3.13.post20260929 - tokenspeed-scheduler
>=0.1.25 - tokenspeed-smg
==1.10.1.post20260920 - tokenspeed-smg-grpc-proto
==0.4.18.post20260920 - tokenspeed-smg-grpc-servicer
==0.9.1.post20260920 - torchAny version
- torch_memory_saver
==0.0.9.post1 - torchvisionAny version
- tqdmAny version
- transformers
==5.12.0 - uvAny version
- uvicornAny version
- uvloopAny version
- viztracerAny version
- xgrammar
==0.2.3
Related packages
- tokenrlPlaceholder for the upcoming TokenSpeed RL packagePublished from the same repository
- tokenspeed-cutedsl-kdaAOT CuteDSL KDA prefill kernels for TokenSpeedPublished from the same repository
- tokenspeed-kernel-amdTokenSpeed AMD-specific high-performance kernels.Published from the same repository
- tokenspeed-kernel-npuReserved placeholder for future TokenSpeed NPU kernel support.Published from the same repository
- tokenspeed-mlaSpeed-of-light TokenSpeed MLA kernels.Published from the same repository
- tokenspeed-situAOT TensorRT-LLM-Gen MXFP4+SiTU MoE kernel bundlePublished from the same repository
- autogluon-coreFast and Accurate ML in 3 Lines of CodeSame primary category
- autogluon-commonFast and Accurate ML in 3 Lines of CodeSame primary category
- pyglovePyGlove: A library for manipulating Python objects.Same primary category
- ttnnGeneral compute framework for Tenstorrent devicesSame primary category
- pyg-nightlyGraph Neural Network Library for PyTorchSame primary category
- rapid-peRapidPE: The original low-latency gravitational wave parameter estimation code.Same primary category
Related news
No published news event mentions this package or its repository yet.