[Doc] Standardize serving names and identifiers (#5081)
Signed-off-by: hsliu_ustc <hsliu_ustc@noreply.gitcode.com> Co-authored-by: hsliu_ustc <hsliu_ustc@noreply.gitcode.com>
This commit is contained in:
1 parent
66b9ad287a
commit
625892032b
45 files changed
+223
-87
No files matched your search
@@ -83,7 +83,7 @@ When constructing `OmniDiffusionConfig` directly:
|
||||
from vllm_omni.diffusion.data import AttentionConfig, AttentionSpec, OmniDiffusionConfig
|
||||
|
||||
config = OmniDiffusionConfig(
|
||||
attention_config=AttentionConfig(
|
||||
diffusion_attention_config=AttentionConfig(
|
||||
default=AttentionSpec(backend="FLASH_ATTN"),
|
||||
per_role={
|
||||
"cross": AttentionSpec(backend="TORCH_SDPA"),
|
||||
|
||||
@@ -33,7 +33,7 @@ m = Omni(model="Wan-AI/Wan2.2-T2V-A14B-Diffusers", enable_cpu_offload=True)
|
||||
|
||||
**CLI:**
|
||||
```bash
|
||||
vllm-omni serve diffusion Wan-AI/Wan2.2-T2V-A14B-Diffusers --enable-cpu-offload
|
||||
vllm serve Wan-AI/Wan2.2-T2V-A14B-Diffusers --omni --enable-cpu-offload
|
||||
```
|
||||
|
||||
### To Support a Model
|
||||
@@ -146,10 +146,10 @@ m = Omni(model="Wan-AI/Wan2.2-I2V-A14B-Diffusers", enable_layerwise_offload=True
|
||||
**CLI:**
|
||||
```bash
|
||||
# Text-to-video
|
||||
vllm-omni serve diffusion Wan-AI/Wan2.2-T2V-A14B-Diffusers --enable-layerwise-offload
|
||||
vllm serve Wan-AI/Wan2.2-T2V-A14B-Diffusers --omni --enable-layerwise-offload
|
||||
|
||||
# Or image-to-video
|
||||
vllm-omni serve diffusion Wan-AI/Wan2.2-I2V-A14B-Diffusers --enable-layerwise-offload
|
||||
vllm serve Wan-AI/Wan2.2-I2V-A14B-Diffusers --omni --enable-layerwise-offload
|
||||
```
|
||||
|
||||
### To Support a Model
|
||||
|
||||
@@ -257,7 +257,7 @@ python end2end.py --model ByteDance-Seed/BAGEL-7B-MoT \
|
||||
| :------- | :--- | :------ | :---------- |
|
||||
| `--deploy-config` | string | `None` | Path to deploy YAML (auto-detected if omitted) |
|
||||
| `--stage-configs-path` | string | `None` | [Deprecated] Legacy path to `stage_args` YAML; prefer `--deploy-config` |
|
||||
| `--worker-backend` | choice | `process` | `process` or `ray` |
|
||||
| `--worker-backend` | choice | `multi_process` | `multi_process` or `ray` |
|
||||
| `--ray-address` | string | `None` | Ray cluster address |
|
||||
| `--quantization` | string | `None` | Quantization method (e.g. `fp8`) |
|
||||
| `--log-stats` | flag | `False` | Enable statistics logging |
|
||||
|
||||
@@ -26,18 +26,22 @@ Stage 0 (AR Model) Stage 1 (Diffusion)
|
||||
|
||||
```python
|
||||
from vllm_omni.entrypoints.omni import Omni
|
||||
from vllm_omni.inputs.data import OmniDiffusionSamplingParams
|
||||
|
||||
if __name__ == "__main__":
|
||||
omni = Omni(model="zai-org/GLM-Image")
|
||||
outputs = omni.generate(
|
||||
"A photorealistic mountain landscape at sunset",
|
||||
sampling_params={
|
||||
"height": 1024,
|
||||
"width": 1024,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 1.5,
|
||||
"seed": 42,
|
||||
},
|
||||
sampling_params_list=[
|
||||
omni.default_sampling_params_list[0],
|
||||
OmniDiffusionSamplingParams(
|
||||
height=1024,
|
||||
width=1024,
|
||||
num_inference_steps=50,
|
||||
guidance_scale=1.5,
|
||||
seed=42,
|
||||
),
|
||||
],
|
||||
)
|
||||
outputs[0].request_output.images[0].save("output.png")
|
||||
```
|
||||
@@ -46,6 +50,7 @@ if __name__ == "__main__":
|
||||
|
||||
```python
|
||||
from vllm_omni.entrypoints.omni import Omni
|
||||
from vllm_omni.inputs.data import OmniDiffusionSamplingParams
|
||||
|
||||
if __name__ == "__main__":
|
||||
omni = Omni(model="zai-org/GLM-Image")
|
||||
@@ -56,13 +61,16 @@ if __name__ == "__main__":
|
||||
"image": "input.png",
|
||||
},
|
||||
},
|
||||
sampling_params={
|
||||
"height": 1024,
|
||||
"width": 1024,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 1.5,
|
||||
"seed": 42,
|
||||
},
|
||||
sampling_params_list=[
|
||||
omni.default_sampling_params_list[0],
|
||||
OmniDiffusionSamplingParams(
|
||||
height=1024,
|
||||
width=1024,
|
||||
num_inference_steps=50,
|
||||
guidance_scale=1.5,
|
||||
seed=42,
|
||||
),
|
||||
],
|
||||
)
|
||||
outputs[0].request_output.images[0].save("output.png")
|
||||
```
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# MiMo-Audio Offline Inference
|
||||
# MiMo-Audio: Offline inference
|
||||
|
||||
Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/mimo_audio>.
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Qwen2.5-Omni
|
||||
# Qwen2.5-Omni: Offline inference
|
||||
|
||||
Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/qwen2_5_omni>.
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Qwen3-Omni
|
||||
# Qwen3-Omni: Offline inference
|
||||
|
||||
Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/qwen3_omni>.
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# AURA Omni Pipeline
|
||||
# AURA Omni: Online serving
|
||||
|
||||
`aura_omni` wires ASR, AURA, and Qwen3-TTS into one vLLM-Omni pipeline:
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Online serving Example of vLLM-Omni for MiMo-Audio
|
||||
# MiMo-Audio: Online serving
|
||||
|
||||
Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/online_serving/mimo_audio>.
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Qwen2.5-Omni
|
||||
# Qwen2.5-Omni: Online serving
|
||||
|
||||
Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/online_serving/qwen2_5_omni>.
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Qwen3-Omni
|
||||
# Qwen3-Omni: Online serving
|
||||
|
||||
Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/online_serving/qwen3_omni>.
|
||||
|
||||
|
||||
Reference in new issue
Block a user