-
### What
The living doc is the main place for the end-user for information on what to do after the superwerker installation. We want to make it easier to understand the individual features of super…
-
### Prerequisites
* [ ] Aqara E1 TRV
Zigbee2MQTT
```
{
"away_preset_temperature": "5.0",
"battery": 0,
"calibrated": true,
"child_lock": false,
"device_temperature": 2…
-
### 🚀 The feature, motivation and pitch
do you plan to support "suffix" of "v1/completions"
### Alternatives
_No response_
### Additional context
_No response_
### Before submittin…
-
### 🚀 The feature, motivation and pitch
Such as topic
### Alternatives
_No response_
### Additional context
_No response_
### Before submitting a new issue...
- [X] Make sure you already search…
-
### Your current environment
Missing v0.6.3.post1-cu118-cp310.whl. Can share it? Thanks so much
### How you are installing vllm
Missing v0.6.3.post1-cu118-cp310.whl. Can share it? Thanks so much
#…
-
### The model to consider.
https://huggingface.co/BAAI/bge-m3
### The closest model vllm already supports.
_No response_
### What's your difficulty of supporting the model you want?
_No response_…
-
### 🚀 The feature, motivation and pitch
When generating multiple answers of the same prompt, will vLLM store the cache of the prompt to speed up?
Can you tell me more technical details?
Thanks!
##…
-
### The model to consider.
https://huggingface.co/lj1995/GPT-SoVITS
### The closest model vllm already supports.
_No response_
### What's your difficulty of supporting the model you want?
_No res…
-
### Your current environment
vllm==0.6.1.post1
vllm-flash-attn==2.6.1
![image](https://github.com/user-attachments/assets/d55dd181-d723-4254-9337-4e18f8c417fa)
### How would you like to use vllm…
-
### 📚 The doc issue
in examples/offline_inference_openai.md, the linked examples/openai_example_batch.jsonl uses max_completion_tokens instead of max_tokens, causing an error when the example is run.…