Run Giant LLMs on Low-End Hardware. Democratizing AI.
Project description
NanoFlow-Z
NanoFlow-Z is a memory-efficient LLM streaming engine designed for edge deployment, enabling large language models to run on resource-constrained devices through aggressive memory management and asynchronous weight streaming.
Mission
- en: Streaming Intelligence to the Edge
- fr: Intelligence en continu à la périphérie
- de: Streaming-Intelligenz für Edge-Geräte
- jp: エッジへのストリーミングインテリジェンス
Philosophy
"Zousko: 'A world where the best is within reach'"
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file nanoflow_z-1.0.1.tar.gz.
File metadata
- Download URL: nanoflow_z-1.0.1.tar.gz
- Upload date:
- Size: 5.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4901276ef9d7d1fa494fb2f2e46d4f6b3fe77704454659dc6d015481cacc04e8
|
|
| MD5 |
4d3e223370bfabd73c1ebf95425d3af2
|
|
| BLAKE2b-256 |
822ef57f2e882f387341f492151b968daf9ae81ee2a1cf28a5db873ea7565ef8
|
File details
Details for the file nanoflow_z-1.0.1-py3-none-any.whl.
File metadata
- Download URL: nanoflow_z-1.0.1-py3-none-any.whl
- Upload date:
- Size: 6.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bcc21e98714f5e501298820b809dbe8f28a9270d3f767d663b99facc94881d38
|
|
| MD5 |
0a56cdf33efa82b6431f2819cfd5f078
|
|
| BLAKE2b-256 |
e706ad1dcdc79d7e67642cd1516435d1566054365259c3f7d73fe8132c2522c2
|
