README / README.md
88plug-bot's picture
Org card: catalog 10/48 product_done
124cb87 verified
|
Raw
History Blame Contribute Delete
4.1 kB
metadata
title: 88plug

88plug

Post-training quantization for production GPU inference


What we publish

Canonical catalog: 48 repos · product_done: 10/48 (gold/provisional + smoke=pass + HF).

Compressed-tensors models quantized for native vLLM deployment. No extra flags, no monkey-patching — weights load automatically on any Ampere+ GPU.

Format Precision Method Use case
W8A16 INT8 weights · BF16 activations compressed-tensors PTQ Max throughput, near-lossless quality
W4A16 INT4 weights · BF16 activations AutoRound (iters=200) Lowest VRAM footprint, high accuracy

Quick start

pip install vllm>=0.21.0

vllm serve 88plug/<model-name> --dtype bfloat16

No --quantization flag required. The compressed-tensors config is embedded in the model weights and auto-detected by vLLM v0.21.0+.

Hardware

  • Quantized on NVIDIA RTX A6000 (48 GB)
  • Tested on Ampere, Ada Lovelace, and Hopper architectures
  • W8A16 models require ~50% the VRAM of BF16
  • W4A16 models require ~25% the VRAM of BF16

Stack