Tutorials Pruna
This tutorial will guide you through the process of using pruna to optimize your model. Looking for pruna_pro tutorials? Check out the Tutorials Pruna Pro page.
Compress with a hq_diffusers
quantizer
and a deepcache
cacher
, and evaluate with throughput
, total time
, clip_score
.
Compress with hqq
quantization and torch_compile
compilation and evaluate with elapsed_time
and perplexity
.
Speed up ASR using the c_whisper
compilation
and whisper_s2t
batching
.
Compile
your model with torch_compile
and openvino
for faster inference.
Speed up diffusers
with torch_compile
compilation
and hqq_diffusers
quantization
.
Evaluate
image generation quality with CMMD
and EvaluationAgent
.
Optimize your diffusion
model with hqq_diffusers
quantization
in 8 bits.
Optimize your diffusion
model with deepcache
caching
.