TheStage AI Docs
TheStage AI Platform
Elastic Models
Qlip
Tutorials
TheStage AI Platform
Elastic Models
Qlip
Tutorials
Quick search
TheStage AI Platform
TheStage AI Platform: SSH Keys and API Tokens
Elastic Models
Get Started
Benchmarking
Product Terms
Qlip
Get Started
Quantization API
Nvidia Compilation and Inference API
Apple Compilation and Inference API
Algorithms API
Automated Acceleration API
Product Terms
Tutorials
Using 2x faster elastic FLUX schnell
Get started with 4x faster Elastic LLMs
Basics of Quantization
FLUX Automated Acceleration
Evaluation of Text-to-Image Models with Qlip
Serving ElasticModels on Modal
Flux Caching Tutorial
Docs
»
Index
Index
A
|
B
|
C
|
D
|
E
|
F
|
G
|
I
|
L
|
M
|
N
|
O
|
Q
|
R
|
S
|
U
|
W
A
activations_round() (qlip.quantization.QuantizationManager method)
add_builder_flag() (qlip.compiler.nvidia.NvidiaBuilderConfig method)
add_infsession() (qlip.inference.nvidia.NvidiaMemoryManager method)
allocate_device_memory() (qlip.inference.nvidia.NvidiaMemoryManager method)
allocate_input_memory() (qlip.inference.nvidia.NvidiaMemoryManager method)
allocate_max_device_memory() (qlip.inference.nvidia.NvidiaInferenceManager method)
allocate_memory() (qlip.inference.nvidia.NvidiaMemoryManager method)
allocate_output_memory() (qlip.inference.nvidia.NvidiaMemoryManager method)
AppleBuilderConfig (class in qlip.compiler.apple)
AppleCompileManager (class in qlip.compiler.apple)
AppleInferenceManager (class in qlip.inference.apple)
AppleSessionConfig (class in qlip.inference.apple)
apply() (qlip_algorithms.anna.BagOfAlgorithms.BagOfAlgorithms method)
auto_setup() (qlip.inference.apple.AppleInferenceManager method)
(qlip.inference.nvidia.NvidiaInferenceManager method)
B
backend (qlip.compiler.apple.AppleCompileManager attribute)
(qlip.compiler.nvidia.NvidiaCompileManager attribute)
(qlip.inference.apple.AppleInferenceManager attribute)
(qlip.inference.nvidia.NvidiaInferenceManager attribute)
C
calibrate() (qlip_algorithms.anna.BagOfAlgorithms.BagOfAlgorithms method)
collect_inputs() (qlip.compiler.apple.AppleCompileManager method)
(qlip.compiler.module.CompiledModule method)
(qlip.compiler.nvidia.NvidiaCompileManager method)
collect_shapes() (qlip.compiler.module.CompiledModule method)
compile() (qlip.compiler.apple.AppleCompileManager method)
(qlip.compiler.module.CompiledModule method)
(qlip.compiler.nvidia.NvidiaCompileManager method)
(qlip.inference.cuda_graph.CudaGraphManager class method)
CompiledModule (class in qlip.compiler.module)
(class in qlip.inference.module)
configure_equalization() (qlip_algorithms.quantization.SmoothQuant.SmoothQuant method)
configure_model() (qlip_algorithms.quantization.PostTrainingQuantization.PostTrainingQuantization method)
configure_quantization() (qlip_algorithms.quantization.SmoothQuant.SmoothQuant method)
CudaGraphManager (class in qlip.inference.cuda_graph)
D
deallocate_memory() (qlip.inference.nvidia.NvidiaMemoryManager method)
E
enable() (qlip.compiler.apple.AppleCompileManager method)
(qlip.compiler.module.CompiledModule method)
(qlip.compiler.nvidia.NvidiaCompileManager method)
(qlip.quantization.QuantizationManager method)
enable_cuda_graph() (qlip.inference.cuda_graph.CudaGraphManager class method)
export_mode() (qlip.compiler.module.CompiledModule method)
extend() (qlip.quantization.QuantizationManager method)
extend_infsessions() (qlip.inference.nvidia.NvidiaMemoryManager method)
extra_repr() (qlip.compiler.module.CompiledModule method)
(qlip.inference.module.CompiledModule method)
extract_device_memory_size() (qlip.inference.nvidia.NvidiaMemoryManager method)
extract_input_memory_size() (qlip.inference.nvidia.NvidiaMemoryManager method)
extract_output_memory_size() (qlip.inference.nvidia.NvidiaMemoryManager method)
F
flush_shapes() (qlip.compiler.module.CompiledModule method)
forward() (qlip.compiler.module.CompiledModule method)
(qlip.inference.module.CompiledModule method)
from_compilemanager() (qlip.inference.apple.AppleInferenceManager class method)
(qlip.inference.nvidia.NvidiaInferenceManager class method)
fuse_scales() (qlip_algorithms.quantization.SmoothQuant.SmoothQuant method)
G
get_algorithms() (qlip_algorithms.anna.BagOfAlgorithms.BagOfAlgorithms method)
get_memory_manager() (qlip.inference.nvidia.NvidiaInferenceManager method)
get_quantization_parameters() (qlip.quantization.QuantizationManager method)
get_quantizers() (qlip.quantization.QuantizationManager method)
I
is_active (qlip.inference.nvidia.NvidiaMemoryManager property)
L
load() (qlip.compiler.module.CompiledModule method)
(qlip.inference.module.CompiledModule method)
M
make_param_groups() (qlip.quantization.QuantizationManager static method)
N
need_calibration() (qlip_algorithms.anna.BagOfAlgorithms.BagOfAlgorithms method)
NvidiaBuilderConfig (class in qlip.compiler.nvidia)
NvidiaCompileManager (class in qlip.compiler.nvidia)
NvidiaInferenceManager (class in qlip.inference.nvidia)
NvidiaMemoryManager (class in qlip.inference.nvidia)
NvidiaSessionConfig (class in qlip.inference.nvidia)
O
original_device (qlip.compiler.module.CompiledModule property)
(qlip.inference.module.CompiledModule property)
Q
qlip.analysis.loss.BaseConvexLoss (built-in class)
qlip.analysis.loss.KLDivergenceConvexLoss (built-in class)
qlip.analysis.loss.MSEConvexLoss (built-in class)
qlip_algorithms.anna.Analyser (built-in class)
qlip_algorithms.anna.ANNAResult (built-in class)
qlip_algorithms.anna.BagOfAlgorithms (built-in class)
qlip_algorithms.anna.CompositeBag (built-in class)
qlip_algorithms.anna.LLMAnalyser (built-in class)
qlip_algorithms.anna.PipelineAnalyser (built-in class)
qlip_algorithms.anna.PTQBag (built-in class)
qlip_algorithms.anna.SmoothQuantBag (built-in class)
qlip_algorithms.quantization.LSQ (built-in class)
qlip_algorithms.quantization.PostTrainingQuantization (built-in class)
qlip_algorithms.quantization.SmoothQuant (built-in class)
QuantGranularity (class in qlip.quantization)
QuantizationManager (class in qlip.quantization)
QuantScheme (class in qlip.quantization)
R
reallocate_memory() (qlip.inference.nvidia.NvidiaMemoryManager method)
register_audio() (qlip_algorithms.anna.ANNAResult.ANNAResult method)
register_benchmarks() (qlip_algorithms.anna.ANNAResult.ANNAResult method)
register_image() (qlip_algorithms.anna.ANNAResult.ANNAResult method)
register_text() (qlip_algorithms.anna.ANNAResult.ANNAResult method)
register_video() (qlip_algorithms.anna.ANNAResult.ANNAResult method)
remove() (qlip.compiler.apple.AppleCompileManager method)
(qlip.compiler.nvidia.NvidiaCompileManager method)
(qlip.quantization.QuantizationManager method)
replace_modules() (qlip.quantization.QuantizationManager static method)
reset() (qlip.inference.cuda_graph.CudaGraphManager method)
reset_warmup() (qlip.inference.cuda_graph.CudaGraphManager method)
restore() (qlip.inference.cuda_graph.CudaGraphManager class method)
run() (qlip_algorithms.anna.Analyser.Analyser method)
S
save() (qlip_algorithms.anna.ANNAResult.ANNAResult method)
set_axes_names() (qlip.compiler.apple.AppleCompileManager method)
(qlip.compiler.nvidia.NvidiaCompileManager method)
set_axes_profiles() (qlip.compiler.apple.AppleCompileManager method)
(qlip.compiler.nvidia.NvidiaCompileManager method)
set_inference_config() (qlip.compiler.module.CompiledModule method)
(qlip.inference.module.CompiledModule method)
set_observer_sync() (qlip.quantization.QuantizationManager method)
set_skip_n() (qlip.compiler.module.CompiledModule method)
set_stream() (qlip.inference.nvidia.NvidiaMemoryManager method)
set_strongly_typed() (qlip.compiler.nvidia.NvidiaBuilderConfig method)
setup_model() (qlip.compiler.apple.AppleCompileManager method)
(qlip.compiler.nvidia.NvidiaCompileManager method)
(qlip.inference.apple.AppleInferenceManager method)
(qlip.inference.nvidia.NvidiaInferenceManager method)
(qlip.quantization.QuantizationManager method)
(qlip_algorithms.quantization.LSQ.LSQ method)
(qlip_algorithms.quantization.PostTrainingQuantization.PostTrainingQuantization method)
(qlip_algorithms.quantization.SmoothQuant.SmoothQuant method)
setup_modules() (qlip.compiler.apple.AppleCompileManager method)
(qlip.compiler.nvidia.NvidiaCompileManager method)
(qlip.inference.apple.AppleInferenceManager method)
(qlip.inference.nvidia.NvidiaInferenceManager method)
(qlip.quantization.QuantizationManager method)
(qlip_algorithms.quantization.LSQ.LSQ method)
(qlip_algorithms.quantization.PostTrainingQuantization.PostTrainingQuantization method)
(qlip_algorithms.quantization.SmoothQuant.SmoothQuant method)
setup_modules_groups() (qlip.quantization.QuantizationManager method)
shape_profile() (qlip.compiler.apple.AppleCompileManager method)
(qlip.compiler.nvidia.NvidiaCompileManager method)
ShapeProfileManager (class in qlip.compiler.manager)
skip_n() (qlip.compiler.manager.ShapeProfileManager method)
U
unload() (qlip.compiler.module.CompiledModule method)
(qlip.inference.module.CompiledModule method)
W
weights_round() (qlip.quantization.QuantizationManager method)
wrap_modules_groups() (qlip_algorithms.quantization.LSQ.LSQ method)