PyPI page
Home page
Author:
None
License:
Apache-2.0
Summary:
ISAT: Inference Stack Auto-Tuner — 91-command production inference engine with KV cache compression, disaggregated prefill-decode, MoE expert parallelism, model routing/cascade, multi-modal pipelines, RAG engine, long context (100K+), inference compiler, SLO scheduling, prompt caching, AI watermarking, token economics, session management, shadow deployment, and edge-cloud hybrid inference.
Latest version:
0.12.0
Required dependencies:
numpy
|
onnx
Optional dependencies:
cryptography
|
fastapi
|
jinja2
|
mypy
|
onnxruntime
|
onnxruntime-gpu
|
onnxruntime-migraphx
|
onnxruntime-rocm
|
onnxsim
|
optimum
|
pre-commit
|
prometheus-client
|
pydantic
|
pytest
|
pyyaml
|
ruff
|
safetensors
|
scipy
|
tensorflow
|
tf2onnx
|
torch
|
transformers
|
uvicorn
Downloads last day:
22
Downloads last week:
348
Downloads last month:
2,787