---
license: other
license_name: deepseek-license
license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL
base_model: deepseek-ai/DeepSeek-V2-Lite
tags:
- deepseek
- deepseek_v2
- fp8
- quantized
- compressed-tensors
- llmcompressor
library_name: transformers
---

# DeepSeek-V2-Lite-FP8-BLOCK-padded

This model is a **FP8 block-quantized** version of [deepseek-ai/DeepSeek-V2-Lite](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite) with **padding support** for non-divisible dimensions.

## Overview

- **Base Model**: deepseek-ai/DeepSeek-V2-Lite (16B parameters)
- **Quantization**: FP8_BLOCK (128x128 block structure)
- **Purpose**: Demonstrates FP8 block quantization with weight padding for models with dimensions not evenly divisible by block size

## Key Feature: Block Quantization Padding

DeepSeek-V2-Lite has `intermediate_size=10944`, which is not divisible by the block size of 128. This model uses **weight padding** to handle this:

- Original `intermediate_size`: 10944
- Padded `intermediate_size`: 11008 (86 × 128)

The padding is applied during quantization and the config.json reflects the padded dimensions for vLLM compatibility.

## Usage with vLLM

```python
from vllm import LLM, SamplingParams

llm = LLM(
    model="Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded",
    trust_remote_code=True,
    tensor_parallel_size=1,
)

sampling_params = SamplingParams(max_tokens=100, temperature=0.7)
output = llm.generate(["Hello, world!"], sampling_params)
print(output[0].outputs[0].text)
```

**Requirements**: H100 or newer GPU (SM 8.9+) for FP8 block quantization support.

## Quantization Recipe

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier

MODEL_ID = "deepseek-ai/DeepSeek-V2-Lite"

model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID, 
    torch_dtype="auto", 
    trust_remote_code=True, 
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)

# FP8 block quantization - ignore layers with composite dimensions
recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_BLOCK",
    ignore=["lm_head", "re:.*kv_a_proj_with_mqa.*"]
)

oneshot(model=model, recipe=recipe)

model.save_pretrained("DeepSeek-V2-Lite-FP8-BLOCK-padded")
tokenizer.save_pretrained("DeepSeek-V2-Lite-FP8-BLOCK-padded")
```

## Created With

- [llm-compressor](https://github.com/vllm-project/llm-compressor) (with padding support)
- [compressed-tensors](https://github.com/neuralmagic/compressed-tensors) (PR #547)

## Ignored Layers

- `lm_head`: Not quantized (standard practice)
- `kv_a_proj_with_mqa`: Has composite dimensions (512 + 64 = 576) that cannot be safely padded

## License

This model inherits the [DeepSeek Model License](https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL) from the base model.