ComfyUI Node: INT8 Kernel Config

Authored by SparknightLLC

Created

Updated

44 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

loaders

Inputs

model MODEL
run_microbench BOOLEAN
block_m INT
block_n INT
block_k INT
group_size_m INT
num_warps INT
num_stages INT
bench_m INT
bench_k INT
bench_n INT
bench_warmup INT
bench_iterations INT
bench_include_scalar BOOLEAN

Outputs

MODEL

Extension: ComfyUI-INT8-Fast-Fork

Fork of node to load models in INT8 for 1.5~2X Speed gains on 30 series cards. Contains additional fixes and performance improvements.

Authored by SparknightLLC

Looking for a different node?

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more