Qwen2.5-72B-Instruct-fp8-block

Qwen2.5-72B-Instruct — FP8 Block Quantization

This is an FP8-block-quantized derivative of Qwen/Qwen2.5-72B-Instruct, produced using llm-compressor v0.13.1.dev2.

Quantization details

The quantized layers cover all attention projections (q_proj, k_proj, v_proj, o_proj) and MLP projections (gate_proj, up_proj, down_proj) in every decoder layer.

Hardware requirements

FP8 block acceleration requires hardware and a vLLM backend with block-scaled FP8 linear support. This checkpoint was validated on AMD MI350X (CDNA4, gfx950) with ROCm 7.2.3.

Note: Other hardware configurations have not been validated with this checkpoint.

Usage with vLLM

from vllm import LLM, SamplingParams

llm = LLM(
    model="rkayaith/Qwen2.5-72B-Instruct-fp8-block",
    # vLLM auto-detects compressed-tensors format — no --quantization flag needed
)

outputs = llm.generate(
    ["Tell me about AMD MI350X"],
    SamplingParams(max_tokens=200, temperature=0.7),
)
print(outputs[0].outputs[0].text)

Or from the command line:

vllm serve rkayaith/Qwen2.5-72B-Instruct-fp8-block

Comparison variants

This checkpoint is part of a four-format study:

License

This derivative work is distributed under the Qwen License Agreement.

Attribution: Qwen is licensed under the Qwen LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved.

Modifications: The original bfloat16 weights were post-training quantized to dynamic block FP8 format using LLM Compressor v0.13.1.dev2. No fine-tuning or other modifications were made.