[Docs] Remove stale stage config references (#6270)
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
This commit is contained in:
1 parent
efaf4276f9
commit
6f55a06fab
85 files changed
+566
-794
No files matched your search
+1
-1
@@ -328,7 +328,7 @@ def run_multimodal_generation(args) -> None:
|
||||
|
||||
extra_body = {
|
||||
"sampling_params_list": sampling_params_list
|
||||
# Optional, it has a default setting in stage_configs of the corresponding model.
|
||||
# Optional; defaults come from the resolved pipeline and deploy config.
|
||||
}
|
||||
|
||||
# Build messages list (filter None so concurrent tasks get valid structure)
|
||||
|
||||
@@ -415,7 +415,7 @@ def run_multimodal_generation(args, client: OpenAI) -> None:
|
||||
audio_path=audio_path,
|
||||
)
|
||||
extra_body = {
|
||||
# Optional, it has default settings in stage configs. you can override them here.
|
||||
# Optional; defaults come from the resolved pipeline and deploy config.
|
||||
}
|
||||
if args.query_type == "use_audio_in_video":
|
||||
extra_body["mm_processor_kwargs"] = {"use_audio_in_video": True}
|
||||
|
||||
@@ -38,7 +38,7 @@ full-duplex control plane:
|
||||
CUDA_VISIBLE_DEVICES=0 python -m vllm_omni.entrypoints.cli.main serve \
|
||||
/path/to/personaplex-7b-v1 \
|
||||
--omni \
|
||||
--stage-configs-path vllm_omni/deploy/personaplex.yaml
|
||||
--deploy-config vllm_omni/deploy/personaplex.yaml
|
||||
```
|
||||
|
||||
Validate the actual `/v1/realtime?duplex=1` scheduler path with paced 24 kHz
|
||||
|
||||
@@ -51,7 +51,7 @@ code2wav_sampling_params='{
|
||||
"detokenize": true,
|
||||
"repetition_penalty": 1.1
|
||||
}'
|
||||
# Above is optional, it has a default setting in stage_configs of the corresponding model.
|
||||
# The block above is optional; defaults come from the resolved pipeline and deploy config.
|
||||
|
||||
# Define URLs for assets
|
||||
MARY_HAD_LAMB_AUDIO_URL="https://vllm-public-assets.s3.us-west-2.amazonaws.com/multimodal_asset/mary_had_lamb.ogg"
|
||||
|
||||
@@ -513,7 +513,7 @@ The script supports the following arguments:
|
||||
vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
|
||||
```
|
||||
|
||||
If you have custom stage configs file:
|
||||
If you have a custom deploy config file:
|
||||
```bash
|
||||
vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091 --deploy-config /path/to/deploy_config_file
|
||||
```
|
||||
|
||||
@@ -50,7 +50,7 @@ code2wav_sampling_params='{
|
||||
"detokenize": true,
|
||||
"repetition_penalty": 1.1
|
||||
}'
|
||||
# Above is optional, it has a default setting in stage_configs of the corresponding model.
|
||||
# The block above is optional; defaults come from the resolved pipeline and deploy config.
|
||||
|
||||
# Define URLs for assets
|
||||
MARY_HAD_LAMB_AUDIO_URL="https://vllm-public-assets.s3.us-west-2.amazonaws.com/multimodal_asset/mary_had_lamb.ogg"
|
||||
|
||||
@@ -15,7 +15,7 @@ so an output is a deterministic function of its own input and nothing else.
|
||||
Measuring replica scaling
|
||||
-------------------------
|
||||
This client is replica-agnostic. Vary the *server's* replica count
|
||||
(`runtime.num_replicas` in the stage config; see run_server.sh) and keep the
|
||||
(`stages[].num_replicas` in the deploy config; see run_server.sh) and keep the
|
||||
client workload fixed, then compare throughput:
|
||||
|
||||
N=1 -> baseline
|
||||
|
||||
@@ -189,5 +189,5 @@ Async chunk reduces TTFP by **67%** by streaming audio token chunks from Thinker
|
||||
- Check server logs for errors
|
||||
|
||||
### Out of memory
|
||||
- Reduce `gpu_memory_utilization` in stage configs
|
||||
- Reduce `gpu_memory_utilization` in the deploy config
|
||||
- Use a smaller batch size
|
||||
@@ -570,7 +570,7 @@ curl -X POST http://localhost:8091/v1/audio/speech \
|
||||
"response_format": "pcm"
|
||||
}' --no-buffer | play -t raw -r 24000 -e signed -b 16 -c 1 -
|
||||
```
|
||||
Raw PCM streaming requires `stream_format="audio"`, `response_format="pcm"`, and `async_chunk: true` on the stage config (default in `qwen3_tts.yaml`). `speed` is not supported when streaming.
|
||||
Raw PCM streaming requires `stream_format="audio"`, `response_format="pcm"`, and `async_chunk: true` in the deploy config (default in `qwen3_tts.yaml`). `speed` is not supported when streaming.
|
||||
|
||||
### Streaming WebSocket
|
||||
The `/v1/audio/speech/stream` endpoint accepts text incrementally and synthesizes the buffered text as one continuous request on `input.done`:
|
||||
|
||||
Reference in new issue
Block a user