anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Merge branch 'main' into codex-vae-spatial-decode-auto

Browse Source
This commit is contained in:
Hongsheng Liu authored and GitHub committed 2026-08-12 11:38:12 +08:00
2 parents af1825e07d a15b5b4bcd
commit 879d19c4c2
186 files changed
+10814 -1165
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/diffusion/lora.md
+105 -7
View File
@@ -1,14 +1,18 @@
# LoRA (Low-Rank Adaptation) Guide
LoRA (Low-Rank Adaptation) enables fine-tuning diffusion models by adding trainable low-rank matrices to existing model weights. vLLM-Omni currently supports PEFT-style LoRA adapters, allowing you to customize model behavior without modifying the base model weights.
LoRA (Low-Rank Adaptation) enables fine-tuning diffusion models by adding trainable low-rank matrices to existing model weights. vLLM-Omni supports two LoRA backends: **PEFT** for PEFT-style adapters, and **Distill** usually for few-steps inference. **PEFT** backend allows you to customize model behavior without modifying the base model weights. **Distill** backend fuses LoRA weights into the base model at initialization.
## Overview
LoRA adapters are lightweight, model-specific fine-tuning weights that can be dynamically loaded and applied to diffusion models. vLLM-Omni uses a unified LoRA handling mechanism similar to vLLM with LRU cache management.
LoRA adapters are lightweight, model-specific fine-tuning weights that can be applied to diffusion models in two ways:
- **PEFT backend** (`--lora-backend peft`, default): Loads a PEFT-format adapter folder via `DiffusionLoRAManager`. Adapters are cached (LRU) and activated per request via `LoRARequest`. It uses a unified LoRA handling mechanisms similar to vLLM with LRU cache management.
- **Distill backend** (`--lora-backend distill`): Calls `pipeline.load_lora_weights` once at initialization to fuse one or more concrete checkpoint files directly into the base weights. Typically used for distilled few-step LoRAs (e.g. Lightning, LightX2V).
## LoRA Adapter Format
LoRA adapters must be in **PEFT (Parameter-Efficient Fine-Tuning)** format. A typical LoRA adapter directory structure:
### PEFT (Parameter-Efficient Fine-Tuning) format (default)
A typical PEFT-format LoRA adapter directory structure:
```
lora_adapter/
@@ -25,19 +29,20 @@ The `adapter_config.json` file contains metadata about the LoRA adapter, includi
### Offline Inference
#### Pre-loaded LoRA
#### PEFT backend: pre-loaded LoRA
Load a LoRA adapter at initialization. This adapter is pre-loaded into the cache and can be activated by requests:
Load a PEFT-format LoRA adapter at initialization. The adapter is pre-loaded into the cache and can be activated per request:
```python
from vllm_omni import Omni
from vllm_omni.lora.request import LoRARequest
lora_path="/path/to/lora_adapter"
lora_path = "/path/to/lora_adapter"
omni = Omni(
model="stabilityai/stable-diffusion-3.5-medium",
lora_path=lora_path
lora_path=lora_path,
lora_backend="peft", # default, can be omitted
)
lora_request = LoRARequest(
@@ -53,6 +58,98 @@ outputs = omni.generate(
)
```
#### Distill backend: fuse distilled LoRA at init
For distilled few-step LoRAs, pass `lora_backend="distill"` together with one or more concrete `.safetensors` files. The weights are fused into the base model once at init; subsequent `generate()` calls do not need a `LoRARequest`.
##### Supported pipelines
For Qwen-Image and Wan pipelines, the distill backend calls `pipeline.load_lora_weights(...)` during worker initialization.
| Pipeline | Supported distilled LoRA repo | Notes |
|----------|--------------------------------|-------|
| `QwenImagePipeline` | `lightx2v/Qwen-Image-2512-Lightning` | Used with Qwen-Image-2512 Lightning-style few-step inference. |
| `Wan22Pipeline` | `lightx2v/Wan2.1-Distill-Loras`, `lightx2v/Wan2.2-Distill-Loras` | Wan2.1 uses one LoRA file. For dual-transformer Wan2.2 MoE, pass high-noise then low-noise LoRA files. |
| `Wan22I2VPipeline` | `lightx2v/Wan2.2-Distill-Loras` | For dual-transformer Wan2.2 MoE, pass high-noise then low-noise LoRA files. |
Other diffusion pipelines are not currently listed as supporting distilled LoRA. Use the PEFT backend for request-time adapters, or bake converted weights into a local Diffusers directory before serving.
Single-file example (Qwen-Image-Lightning):
```python
from vllm_omni import Omni
omni = Omni(
model="Qwen/Qwen-Image-2512",
lora_path="/path/to/Qwen-Image-2512-Lightning.safetensors",
lora_backend="distill",
)
outputs = omni.generate(prompt="A piece of cheesecake")
```
Multi-file example (Wan2.2 MoE, high + low noise):
```python
from vllm_omni import Omni
omni = Omni(
model="Wan-AI/Wan2.2-T2V-A14B-Diffusers",
lora_path=[
"/path/to/wan2.2_high_noise_lora.safetensors", # -> transformer
"/path/to/wan2.2_low_noise_lora.safetensors", # -> transformer_2
],
lora_backend="distill",
)
```
The CLI examples under `examples/offline_inference/` accept the same flags, e.g.:
```bash
python examples/offline_inference/text_to_video/text_to_video.py \
--model Wan-AI/Wan2.2-T2V-A14B-Diffusers \
--lora-backend distill \
--lora-path /path/to/high.safetensors /path/to/low.safetensors \
--prompt "A cat playing with yarn"
```
##### Online serving
Distilled LoRAs can also be fused when an online diffusion server starts. The
adapter remains active for the lifetime of that server, so requests do not pass
a per-request `lora` field.
```bash
vllm serve Qwen/Qwen-Image-2512 \
--omni \
--port 8091 \
--lora-backend distill \
--lora-path /path/to/Qwen-Image-2512-Lightning-4steps.safetensors
```
Then send a normal generation request with the sampling settings expected by
the distilled checkpoint:
```bash
curl -s http://localhost:8091/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"messages": [
{"role": "user", "content": "A Chinese female college student, around 20 years old, with a very short haircut that conveys a gentle, artistic vibe. Her hair naturally falls to partially cover her cheeks, projecting a tomboyish yet charming demeanor. She has cool-toned fair skin and delicate features, with a slightly shy yet subtly confident expression—her mouth crooked in a playful, youthful smirk. She wears an off-shoulder top, revealing one shoulder, with a well-proportioned figure. The image is framed as a close-up selfie: she dominates the foreground, while the background clearly shows her dormitory—a neatly made bed with white linens on the top bunk, a tidy study desk with organized stationery, and wooden cabinets and drawers. The photo is captured on a smartphone under soft, even ambient lighting, with natural tones, high clarity, and a bright, lively atmosphere full of youthful, everyday energy."}
],
"extra_body": {
"height": 1024,
"width": 1024,
"num_inference_steps": 4,
"true_cfg_scale": 1.0,
"seed": 42
}
}' | jq -r '.choices[0].message.content[0].image_url.url' | cut -d',' -f2 | base64 -d > qwen_image_distill_lora_output.png
```
For Wan2.2 MoE serving, pass the high-noise checkpoint first and the low-noise
checkpoint second to `--lora-path`.
!!! note "Server-side Path Requirement"
The LoRA adapter path (`local_path`) must be readable on the **server** machine. If your client and server are on different machines, ensure the LoRA adapter is accessible via a shared mount or copied to the server.
@@ -141,6 +238,7 @@ Notes:
- This route avoids runtime LoRA loading changes in vLLM-Omni when you choose to bake converted weights into a local Diffusers directory.
- Output quality and speed depend on the replacement checkpoints and sampling params you choose.
- If you only need to fuse distilled LoRAs into a Wan2.2 checkpoint at load time (without the full LightX2V convert + assemble pipeline), you can instead pass them directly via `--lora-backend distill --lora-path <high>.safetensors <low>.safetensors`. See the [Distill backend](#distill-backend-fuse-distilled-lora-at-init) section above.
## See Also
docs/user_guide/diffusion/startup_and_loading.md
+60
View File
@@ -0,0 +1,60 @@
# Diffusion Startup and Loading
Large diffusion models can take several minutes to load at startup. vLLM-Omni
loads safetensors shards in parallel to reduce this initialization time.
Multi-thread weight loading is enabled by default with four threads. No
configuration is needed for the default behavior.
## Configuration
| Parameter | CLI flag | Default | Description |
| --- | --- | --- | --- |
| `enable_multithread_weight_load` | `--disable-multithread-weight-load` | `True` | Pass the flag to disable multi-thread loading |
| `num_weight_load_threads` | `--num-weight-load-threads` | `4` | Number of parallel weight-loading threads |
!!! tip
The default balances startup speed and disk I/O contention. Fast NVMe
storage may benefit from more threads, while network storage or hard disks
may not.
## Online Serving
```bash
# Default: multi-thread loading with four threads
vllm serve Qwen/Qwen-Image --omni --port 8091
# Increase the thread count
vllm serve Wan-AI/Wan2.2-I2V-A14B-Diffusers --omni \
--num-weight-load-threads 8
# Disable multi-thread loading
vllm serve Qwen/Qwen-Image --omni --disable-multithread-weight-load
```
## Offline Inference
```python
from vllm_omni import Omni
# Default: multi-thread loading with four threads
omni = Omni(model="Qwen/Qwen-Image")
# Increase the thread count
omni = Omni(
model="Wan-AI/Wan2.2-I2V-A14B-Diffusers",
num_weight_load_threads=8,
)
```
## Reference Benchmarks
The following measurements were collected on NVIDIA H800 hardware. Treat them
as reference results rather than a guarantee for other storage or hardware
configurations.
| Model | Sequential loading | Multi-thread loading | Speedup |
| --- | ---: | ---: | ---: |
| **Qwen/Qwen-Image** (53.7 GiB) | 168 s | 27 s | **6.2x** |
| **Wan-AI/Wan2.2-I2V-A14B-Diffusers** (64.5 GiB) | 283 s | 56 s | **5.1x** |
docs/user_guide/diffusion_features.md
+37 -85
View File
@@ -49,7 +49,7 @@ Parallelism methods distribute computation across GPUs without quality loss (mat
| Method | Description | Best For |
|--------|-------------|----------|
| **[Multi-Thread Weight Loading](#multi-thread-weight-loading)** | Loads safetensors shards in parallel using a thread pool | All diffusion models; reduces startup from minutes to seconds |
| **[Multi-Thread Weight Loading](diffusion/startup_and_loading.md)** | Loads safetensors shards in parallel using a thread pool | All diffusion models; reduces startup from minutes to seconds |
**Note:** Some acceleration methods can be combined together for optimized performance. See [Feature Compatibility Table](#feature-compatibility) and [Feature Compatibility Tutorial](feature_compatibility.md) for detailed configuration examples.
@@ -100,7 +100,9 @@ The following tables show which models support each feature:
- **🔀SP (Ulysses & Ring)**: Includes both Ulysses-SP and Ring-Attention methods
- ✅ = Fully supported
- ✅* = Supported with the constraint listed below the table
- ❌ = Not supported
- ❓ = Not verified; not recommended
> Notes:
@@ -119,7 +121,7 @@ The following tables show which models support each feature:
| **FLUX.2-dev** | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| **GLM-Image** | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| **Hidream-I1-Full** | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
| **HunyuanImage3** | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ |
| **HunyuanImage3** | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅* |
| **Krea 2** | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ (decode) | ❌ | ❌ |
| **LongCat-Image** | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ |
| **LongCat-Image-Edit** | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ |
@@ -145,6 +147,7 @@ The following tables show which models support each feature:
> 2. `Tongyi-MAI/Z-Image-Turbo` and `SII-GAIR/daVinci-MagiHuman-Base-1080p` are distilled models with minimal NFEs; CFG-Parallel is not necessary.
> 3. Cosmos3 T2I uses `Cosmos3OmniDiffusersPipeline` with `modalities=["image"]`. Model-level CPU offload swaps the nested UND reasoner and GEN generator pathways; layerwise offload remains available for blockwise GEN/UND offload.
> 4. Krea 2 currently supports single-GPU inference plus LoRA, Cache-DiT, HSDP, CPU/layerwise offload, and VAE-patch-parallel (decode). TP/SP/CFG-Parallel are not yet wired. The few-step distilled (Turbo) checkpoint uses `is_distilled=true` (fixed timestep shift `mu=1.15`); generate at 2048x2048 by default with `num_inference_steps≈8` and `guidance_scale=0`. The Raw checkpoint uses 1024x1024, `num_inference_steps=28`, and `guidance_scale=4.5`.
> 5. HunyuanImage3 supports step execution. Multi-request step execution requires `TORCH_SDPA`; see [Diffusion Execution Modes](diffusion/execution_modes.md#step-execution).
### VideoGen
@@ -155,13 +158,16 @@ The following tables show which models support each feature:
| **Wan2.1-VACE** | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ (decode) | ❌ | ❌ |
| **LTX-2** | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ (decode) | ❌ | ❌ |
| **LTX-2.3** | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ (decode) | ❌ | ❌ |
| **Helios** | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| **Helios** | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ✅* |
| **HunyuanVideo-1.5 T2V I2V** | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ (encode/decode) | ✅ | ❌ |
| **DreamID-Omni** | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| **Cosmos3** | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ (encode/decode) | ✅ | ❌ |
| **LongCat-Video-Avatar-1.5** | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
| **MiniMax-H3** | ✅ (FL2VA) | ✅ | ✅ | ❌ | ✅ (DiT/TE) | ❌ | ✅ | ✅ | ✅ (tile) | ✅ (DiT) | ❌ |
> **Step execution note:** Helios supports single-request step execution only;
> use `max_num_seqs=1`.
**Frame Interpolation Support**
- **Supported**: Wan2.2 text-to-video, image-to-video, and TI2V pipelines
@@ -190,7 +196,7 @@ The following tables show which models support each feature:
| **🔀Ring-Attn** | ✅ | ✅ | ✅ | | | | | | | | | | | |
| **🔀CFG-Parallel** | ✅ | ✅ | ✅ | ✅ | | | | | | | | | | |
| **🔀Tensor Parallel** | ✅ | ✅ | ✅ | ✅ | ✅ | | | | | | | | | |
| **🔀HSDP** | ❓ | ❓ | ❓ | ❓ | ❓ | ❌ | | | | | | | | |
| **🔀HSDP** | ❓ | ❓ | ✅ | ❓ | ✅ | ❌ | | | | | | | | |
| **🔀Expert Parallel** | ❓ | ❓ | ❓ | ❓ | ❓ | ❓ | ❓ | | | | | | | |
| **💾CPU Offloading (Layerwise)** | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | | | | | | |
| **💾CPU Offloading (Module-wise)** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❓ | ❓ | ❌ | | | | | |
@@ -201,97 +207,43 @@ The following tables show which models support each feature:
!!! info
1. Tensor Parallel and HSDP are not compatible.
1. HSDP can be combined with Ulysses-SP or CFG-Parallel. Tensor Parallel
and HSDP are not compatible; other HSDP combinations in the table
remain unverified.
2. TeaCache and Cache-DiT are not compatible.
3. CPU Offloading (Layerwise) and CPU Offloading (Module-wise) are not compatible.
4. CPU Offloading (Layerwise) supports single-card for now.
5. Using FP8-Quant as an example of qunatization methods.
4. The CPU Offloading (Layerwise) row describes local layerwise offload.
Multi-device Distributed Layerwise Offload has a separate topology and
compatibility matrix in the [CPU Offloading guide](diffusion/cpu_offload.md#distributed-layerwise-offloading).
5. The compatibility matrix uses FP8 as the representative quantization method.
6. Step Execution is not compatible with any diffusion cache backend. LoRA is supported, but each scheduled batch must use a single adapter (requests with different `lora_request` or `lora_scale` are kept in separate batches).
## Multi-Thread Weight Loading
Large diffusion models can take several minutes to load weights at startup (e.g., ~3 min for Qwen-Image, ~5 min for Wan2.2 I2V 14B). Multi-thread weight loading speeds up this process by loading safetensors shards in parallel using a thread pool instead of sequentially.
This optimization is **enabled by default** with 4 threads. No configuration is needed for the default behavior.
### Configuration
| Parameter | CLI Flag | Default | Description |
|-----------|----------|---------|-------------|
| `enable_multithread_weight_load` | `--disable-multithread-weight-load` | `True` (enabled) | Pass the flag to disable multi-thread loading |
| `num_weight_load_threads` | `--num-weight-load-threads` | `4` | Number of threads for parallel weight loading |
!!! tip
The default of 4 threads balances speed and disk I/O contention. On fast NVMe storage you may benefit from more threads (e.g., 8). On HDD or network storage, the default of 4 avoids saturating I/O bandwidth.
### Online Serving
```bash
# Default (multi-thread enabled, 4 threads)
vllm serve Qwen/Qwen-Image --omni --port 8091
# Custom thread count
vllm serve Wan-AI/Wan2.2-I2V-A14B-Diffusers --omni --num-weight-load-threads 8
# Disable multi-thread loading
vllm serve Qwen/Qwen-Image --omni --disable-multithread-weight-load
```
### Offline Inference
```python
from vllm_omni import Omni
# Default (multi-thread enabled, 4 threads)
omni = Omni(model="Qwen/Qwen-Image")
# Custom thread count
omni = Omni(
model="Wan-AI/Wan2.2-I2V-A14B-Diffusers",
num_weight_load_threads=8,
)
```
### Benchmarks
Measured on NVIDIA H800:
| Model | Before | After | Speedup |
|-------|--------|-------|---------|
| **Qwen/Qwen-Image** (53.7 GiB) | 168s | 27s | **6.2x** |
| **Wan-AI/Wan2.2-I2V-A14B-Diffusers** (64.5 GiB) | 283s | 56s | **5.1x** |
The loading guide now lives at [Diffusion Startup and
Loading](diffusion/startup_and_loading.md). This heading remains so existing
links to this section continue to work.
## Learn More
**Cache Acceleration:**
The Diffusion Acceleration navigation groups the remaining guides as follows:
- **[TeaCache Configuration Guide](diffusion/cache_acceleration/teacache.md)** - Parameter tuning, performance tips, troubleshooting
- **[Cache-DiT Advanced Guide](diffusion/cache_acceleration/cache_dit.md)** - DBCache, TaylorSeer, SCM techniques and optimization
| Area | Guide |
| --- | --- |
| Compatibility | [Feature Compatibility](feature_compatibility.md) |
| CPU offloading | [CPU Offloading](diffusion/cpu_offload.md) |
| Cache acceleration | [TeaCache](diffusion/cache_acceleration/teacache.md), [Cache-DiT](diffusion/cache_acceleration/cache_dit.md) |
| Parallelism | [Parallelism Overview](diffusion/parallelism/overview.md) |
| Attention | [Attention Backends](diffusion/attention_backends.md) |
| Compilation | [Regional Compilation](diffusion/regional_compilation.md) |
| Video extension | [Frame Interpolation](diffusion/frame_interpolation.md) |
| Startup | [Startup and Loading](diffusion/startup_and_loading.md) |
| Adapters | [LoRA](diffusion/lora.md) |
**Parallelism Methods:**
Related cross-model and runtime features are documented separately:
- **[Parallelism Overview](diffusion/parallelism/overview.md)** - Tensor Parallelism, Sequence Parallelism, CFG Parallelism, Pipeline Parallelism, HSDP, and Expert Parallelism
**Memory Optimization:**
- **[CPU Offload Guide](diffusion/cpu_offload.md)** - Offload model components to CPU, reduce GPU memory usage
- **[VAE Parallelism Guide](diffusion/parallelism/vae_parallelism.md)** - Distribute VAE decode work across GPUs for high-resolution images and videos
- **[Quantization](quantization/overview.md)** - Quantization methods for diffusion, multi-stage omni/TTS, and multi-stage diffusion models
**Extensions:**
- **[LoRA Inference Guide](diffusion/lora.md)** - Low-Rank Adaptation for style customization and fine-tuning
- **[Frame Interpolation Guide](diffusion/frame_interpolation.md)** - Worker-side post-generation video frame interpolation for smoother motion
**Execution Modes:**
- **[Diffusion Execution Modes](diffusion/execution_modes.md)** - Configure request batching, step execution, continuous batching, and streaming output
**Startup Optimization:**
- **[Multi-Thread Weight Loading](#multi-thread-weight-loading)** - Speed up model startup by loading safetensors shards in parallel
**Advanced Topics:**
- **[Feature Compatibility](feature_compatibility.md)** - How to combine multiple features for maximum performance
- [Quantization](quantization/overview.md) covers diffusion-only models,
multi-stage omni/TTS models, and multi-stage diffusion models.
- [Execution Modes and Streaming](diffusion/execution_modes.md) covers the
diffusion runtime, including batching, step execution, and streaming output.
docs/user_guide/examples/offline_inference/text_to_image.md
+2 -1
View File
@@ -88,8 +88,9 @@ python text_to_image.py \
| `--vae-use-tiling` | flag | off | Enable VAE tiling for memory optimization |
| `--cfg-parallel-size` | int | `1` | Set to `2` to enable CFG Parallel |
| `--enable-cpu-offload` | flag | off | Enable CPU offloading for diffusion models |
| `--lora-path` | str | — | Path to PEFT LoRA adapter folder |
| `--lora-path` | str | — | Path to PEFT LoRA adapter folder or checkpoint file |
| `--lora-scale` | float | `1.0` | Scale factor for LoRA weights |
| `--lora-backend` | str |`"peft"`| LoRA backend for loading LoRA adapters. Default: peft. Available options: peft, distill |
**NextStep-1.1 specific arguments:**
docs/user_guide/examples/offline_inference/text_to_video.md
+3
View File
@@ -125,6 +125,9 @@ python text_to_video.py \
- `--audio-sample-rate`: fallback audio sample rate when the pipeline returns audio.
- `--quantization`: quantization method (`fp8` for FP8, `gguf` for GGUF).
- `--flow-shift`: scheduler flow_shift parameter.
- `--lora-path`: path to PEFT LoRA adapter folder or checkpoint file.
- `--lora-scale`: scale factor for LoRA weights.
- `--lora-backend`: backend for loading LoRA adapters. Default: peft. Available options: peft, distill.
### Wan2.2-specific
docs/user_guide/quantization/overview.md
+15 -15
View File
@@ -12,20 +12,20 @@ For the internal architecture and backend extension points, see the
| Mode | Guide | Description | Methods |
|------|-------|-------------|---------|
| Online quantization | [Online Quantization](online.md) | vLLM-Omni computes quantized weights and scales while loading the model. | FP8 W8A8, Int8 W8A8, MXFP8 W8A8, MXFP4 W4A4 |
| Online quantization | [Online Quantization](online.md) | vLLM-Omni computes quantized weights and scales while loading the model. | FP8 W8A8, Int8 W8A8, BitsAndBytes W4, MXFP8 W8A8, MXFP4 W4A4 |
| Runtime attention quantization | [Quantized KV Cache](quantized_kvcache.md) | vLLM-Omni dynamically quantizes eligible diffusion Flash Attention tensors during inference. | FP8 FA |
| Pre-quantized checkpoints | Method-specific guides | The checkpoint or an offline quantizer provides quantized weights and scales before serving. | ModelOpt, GGUF, AutoRound, msModelSlim, serialized Int8, offline MXFP8, offline MXFP4 DualScale |
| Pre-quantized checkpoints | Method-specific guides | The checkpoint or an offline quantizer provides quantized weights and scales before serving. | ModelOpt, AutoRound, msModelSlim, serialized Int8, offline MXFP8, offline MXFP4 DualScale |
## Hardware Support
| Device | FP8 W8A8 | Int8 W8A8 | ModelOpt | MXFP8 W8A8 | MXFP4 W4A4 | GGUF | AutoRound | msModelSlim |
|--------|----------|-----------|----------|------------|------------|------|-----------|-------------|
| NVIDIA Blackwell GPU (SM 100+) | ✅ | ✅ | ✅ | ⭕ | ⭕ | ✅ | ✅ | ❌ |
| NVIDIA Ada/Hopper GPU (SM 89+) | ✅ | ✅ | ✅ | ⭕ | ⭕ | ✅ | ✅ | ❌ |
| NVIDIA Ampere GPU (SM 80+) | ✅ | ✅ | ⭕ | ⭕ | ⭕ | ✅ | ✅ | ❌ |
| AMD ROCm | ⭕ | ⭕ | ⭕ | ⭕ | ✅ | ⭕ | ⭕ | ❌ |
| Intel XPU | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ | ✅ | ❌ |
| Ascend NPU | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ✅ |
| Device | FP8 W8A8 | Int8 W8A8 | BitsAndBytes W4 | ModelOpt | MXFP8 W8A8 | MXFP4 W4A4 | AutoRound | msModelSlim |
|--------|----------|-----------|------------------|----------|------------|------------|-----------|-------------|
| NVIDIA Blackwell GPU (SM 100+) | ✅ | ✅ | ✅ | ✅ | ⭕ | ⭕ | ✅ | ❌ |
| NVIDIA Ada/Hopper GPU (SM 89+) | ✅ | ✅ | ✅ | ✅ | ⭕ | ⭕ | ✅ | ❌ |
| NVIDIA Ampere GPU (SM 80+) | ✅ | ✅ | ✅ | ⭕ | ⭕ | ⭕ | ✅ | ❌ |
| AMD ROCm | ⭕ | ⭕ | ❌ | ⭕ | ⭕ | ✅ | ⭕ | ❌ |
| Intel XPU | ⭕ | ⭕ | ❌ | ⭕ | ⭕ | ⭕ | ✅ | ❌ |
| Ascend NPU | ❌ | ✅ | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ |
Legend: `✅` supported, `❌` unsupported, `⭕` not verified in this
guide. FP8 on Ampere may use a weight-only path where available.
@@ -43,10 +43,10 @@ otherwise.
|--------|-------|------|----------------|--------|
| FP8 W8A8 | [FP8](fp8.md) | Online W8A8 or checkpoint FP8 | Qwen-Image; Wan2.2 is not validated | Validated for Qwen-Image family and other DiT models |
| Int8 W8A8 | [Int8](int8.md) | Online or serialized W8A8 | Qwen-Image; Wan2.2 is not validated | Validated for Qwen-Image and Z-Image |
| BitsAndBytes W4 | [BitsAndBytes](bitsandbytes.md) | Online W4 weight-only | Z-Image-Turbo; Qwen-Image/Wan2.2 not validated | Validated for Z-Image-Turbo |
| ModelOpt | [ModelOpt](modelopt.md) | Pre-quantized FP8 checkpoints | Qwen-Image, Z-Image, FLUX.2, HunyuanImage-3.0 | Validated for ModelOpt FP8 diffusion checkpoints |
| MXFP8 W8A8 | [MXFP8](mxfp8.md) | Online W8A8 or offline pre-quantized | Wan2.2-T2V-A14B, I2V-A14B, TI2V-5B | Ascend NPU only; validated for Wan2.2 |
| MXFP4 W4A4 | [MXFP4](mxfp4.md) | `mxfp4`: online single-scale only; `mxfp4_dualscale`: online or offline dual-scale (offline recommended) | Wan2.2-T2V-A14B, I2V-A14B | Ascend NPU only; validated for Wan2.2 A14B cascade models; TI2V-5B not supported; offline `mxfp4_dualscale` uses calibrated `mul_scale` for best accuracy |
| GGUF | [GGUF](gguf.md) | Pre-quantized transformer weights | Qwen-Image | Validated where a model-specific GGUF adapter exists |
| AutoRound | [AutoRound](autoround.md) | Pre-quantized W4A16 checkpoints | FLUX.1-dev; Qwen-Image/Wan2.2 not validated | Checkpoint-driven |
| msModelSlim | [msModelSlim](msmodelslim.md) | Pre-quantized Ascend checkpoints | Wan2.2 recipe; HunyuanImage-3.0 inference target | Ascend/NPU path |
@@ -61,9 +61,9 @@ in BF16 unless the model guide explicitly adds support.
|--------|-------|-------|----------------|--------|
| ModelOpt | [ModelOpt](modelopt.md) | Thinker or language-model checkpoint config | Qwen3-Omni thinker | ModelOpt checkpoint path |
| Int8 | [Int8](int8.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
| BitsAndBytes | [BitsAndBytes](bitsandbytes.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
| MXFP8 | [MXFP8](mxfp8.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
| MXFP4 | [MXFP4](mxfp4.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
| GGUF | [GGUF](gguf.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
| AutoRound | [AutoRound](autoround.md) | Thinker or language-model checkpoint config | Qwen2.5-Omni, Qwen3-Omni | Supported through AutoRound checkpoints |
| msModelSlim | [msModelSlim](msmodelslim.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
@@ -76,10 +76,10 @@ attached to the intended stage rather than applied globally.
|--------|-------|-------|----------------|--------|
| FP8 | [FP8](fp8.md) | Stage-specific DiT or transformer module | BAGEL, GLM-Image | Requires model-specific validation |
| Int8 | [Int8](int8.md) | Stage-specific DiT or transformer module | BAGEL, GLM-Image | Requires model-specific validation |
| BitsAndBytes | [BitsAndBytes](bitsandbytes.md) | Stage-specific transformer or DiT module | BAGEL, GLM-Image | Not validated |
| ModelOpt | [ModelOpt](modelopt.md) | Checkpoint-defined diffusion stage | BAGEL, GLM-Image | Requires model-specific validation |
| MXFP8 | [MXFP8](mxfp8.md) | Stage-specific DiT or transformer module | BAGEL, GLM-Image | Not validated |
| MXFP4 | [MXFP4](mxfp4.md) | Stage-specific DiT or transformer module | BAGEL, GLM-Image | Not validated |
| GGUF | [GGUF](gguf.md) | Stage-specific transformer weights | BAGEL, GLM-Image | No validated adapter listed |
| AutoRound | [AutoRound](autoround.md) | Checkpoint-defined stage | BAGEL, GLM-Image | No validated checkpoint listed |
| msModelSlim | [msModelSlim](msmodelslim.md) | Ascend-generated stage weights | GLM-Image | Requires model-specific adaptation |
@@ -106,7 +106,7 @@ config = build_quant_config({
| Component | Default quantized? | Notes |
|-----------|--------------------|-------|
| Diffusion transformer | Yes | Primary target for FP8, Int8, ModelOpt, MXFP8, MXFP4, GGUF, AutoRound, and msModelSlim |
| Diffusion transformer | Yes | Primary target for FP8, Int8, BitsAndBytes, ModelOpt, MXFP8, MXFP4, AutoRound, and msModelSlim |
| Text encoder | No | Keep BF16 unless a method-specific guide documents support |
| VAE | No | Keep BF16; storage-only paths are method-specific |
| Scheduler/tokenizer | No | Loaded from the base model repository |
@@ -139,8 +139,8 @@ from vllm_omni.quantization import build_quant_config
build_quant_config("fp8")
build_quant_config({"method": "fp8", "activation_scheme": "static"})
build_quant_config("bitsandbytes")
build_quant_config("auto-round", bits=4, group_size=128)
build_quant_config({"method": "gguf", "gguf_model": "/path/to/model.gguf"})
build_quant_config({"transformer": {"method": "fp8"}, "vae": None})
build_quant_config(None)
```