xPyD

Meta-package for the xPyD ecosystem. Installs all components:

pip install xpyd

This installs:

xpyd-proxy — Lightweight Prefill-Decode proxy for disaggregated LLM serving
xpyd-sim — OpenAI-compatible LLM inference simulator
xpyd-bench — Benchmarking & PD ratio planning tool
xpyd-acc — PD disaggregation accuracy diagnostic tool
xpyd-plan — PD ratio planner for optimal node allocation

Individual packages can also be installed separately:

pip install xpyd-proxy  # proxy only
pip install xpyd-sim    # simulator only
pip install xpyd-bench  # benchmark only
pip install xpyd-acc    # accuracy diagnostic only
pip install xpyd-plan   # ratio planner only

License

Apache 2.0

Download files

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

Source Distribution

xpyd-1.5.0.tar.gz (1.4 kB view details)

Uploaded Aug 22, 2026 Source

Built Distribution

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

xpyd-1.5.0-py3-none-any.whl (1.4 kB view details)

Uploaded Aug 22, 2026 Python 3

File details

Details for the file xpyd-1.5.0.tar.gz.

File metadata

Download URL: xpyd-1.5.0.tar.gz
Upload date: Aug 22, 2026
Size: 1.4 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/7.0.0 CPython/3.12.14

File hashes

Hashes for xpyd-1.5.0.tar.gz
Algorithm	Hash digest
SHA256	`7a0616dc6be5f42393f19875a820b0bcbac5e1874ca23f4d98a2793ac691b247`
MD5	`f5407241e70ed28095810eec6a8a2f26`
BLAKE2b-256	`3b32c35e0774dc960bc24ef8f7f290ddbe68e6ce6792c092ad13ebaa805298b0`

See more details on using hashes here.

File details

Details for the file xpyd-1.5.0-py3-none-any.whl.

File metadata

Download URL: xpyd-1.5.0-py3-none-any.whl
Upload date: Aug 22, 2026
Size: 1.4 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/7.0.0 CPython/3.12.14

File hashes

Hashes for xpyd-1.5.0-py3-none-any.whl
Algorithm	Hash digest
SHA256	`3f90b97f0084108fb8fb5d5906d914eae1bfbcb9ff209a7588d0f68e66d86d93`
MD5	`359f1087ac0e4f82d3bd88955681d1b1`
BLAKE2b-256	`6cf5329e0449bb29813b54b5ab8e4959b8fd4ea0cb8a00cf79c731b027411270`