Files
vllm/docs/features/quantization/online.md
T
2026-04-20 06:26:12 -07:00

98 lines
3.0 KiB
Markdown

# Online Quantization
Online quantization lets you take a BF16/FP16 model and quantize its Linear
and MoE weights to lower precision (such as FP8) at load time, without needing
a pre-quantized checkpoint or calibration data. Weights are converted during
model loading and activations are dynamically scaled during each forward pass.
## Quick Start
Pass a scheme name to the `quantization` parameter:
```python
from vllm import LLM
# Per-tensor FP8 quantization (one scale per weight tensor)
llm = LLM("meta-llama/Llama-3.1-8B", quantization="fp8_per_tensor")
# Per-block FP8 quantization (128x128 block scaling for weights and 1x128 block scaling for activations)
llm = LLM("meta-llama/Llama-3.1-8B", quantization="fp8_per_block")
# MXFP8 quantization for weights and activations
llm = LLM("meta-llama/Llama-3.1-8B", quantization="mxfp8")
```
Or with the CLI:
```bash
vllm serve meta-llama/Llama-3.1-8B --quantization fp8_per_tensor
vllm serve meta-llama/Llama-3.1-8B --quantization fp8_per_block
vllm serve meta-llama/Llama-3.1-8B --quantization mxfp8
```
## Supported Schemes
| Scheme | Weight recipe | Activation recipe | Notes |
| ------ | ------------- | ------------------ | ----- |
| `fp8_per_tensor` | fp8_e4m3 data, fp32 per-tensor scale | fp8_e4m3 data, fp32 per-tensor scale | On some GPUs (Ada, Hopper) linear activations use per-token scaling for better performance |
| `fp8_per_block` | fp8_e4m3 data, fp32 per-128x128-block scale | fp8_e4m3 data, fp32 per-1x128-block scale | |
| `mxfp8` | fp8_e4m3 data, e8m0 per-1x32-block scale | fp8_e4m3 data, e8m0 per-1x32-block scale | Requires SM 100+ (Blackwell or newer) for w8a8, other GPUs use a w8a16 fallback |
## Advanced Configuration
For fine-grained control, use a `quantization_config` dictionary.
### Separate Schemes for Dense and MoE Layers
You can apply different quantization schemes to dense linear layers and MoE expert layers:
```python
from vllm import LLM
llm = LLM(
"ibm-granite/granite-3.0-1b-a400m-base",
quantization="fp8_per_tensor",
quantization_config={
"linear_scheme_override": "fp8_per_block",
},
)
```
Or,
```python
from vllm import LLM
llm = LLM(
"ibm-granite/granite-3.0-1b-a400m-base",
quantization="fp8_per_tensor",
quantization_config={
"moe_scheme_override": "fp8_per_block",
},
)
```
### Excluding Layers from Quantization
Use the `ignore` parameter to skip specific layers. It accepts exact layer names and regex patterns (prefixed with `re:`):
```python
from vllm import LLM
llm = LLM(
"ibm-granite/granite-3.0-1b-a400m-base",
quantization="fp8_per_tensor",
quantization_config={
"ignore": [
# exact layer name
"model.layers.1.self_attn.o_proj",
# regex: skip all QKV projections
"re:.*[qkv]_proj",
],
},
)
```
!!! note
For fused layers (e.g., `qkv_proj` which fuses `q_proj`, `k_proj`, `v_proj`), the ignore pattern must match the **unfused** shard names (`q_proj`, `k_proj`, `v_proj`), not the fused name.