[doc] Fold long code blocks to improve readability (#19926)

Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
This commit is contained in:
Reid
2025-06-23 13:24:23 +08:00
committed by GitHub
parent 493c275352
commit f17aec0d63
50 changed files with 3455 additions and 3180 deletions

View File

@@ -43,17 +43,19 @@ llm = LLM(
## Read gptq format checkpoint
```python
from vllm import LLM
import torch
??? Code
# "hxbgsyxh/llama-13b-4bit-g-1" is a pre-quantized checkpoint.
model_id = "hxbgsyxh/llama-13b-4bit-g-1"
llm = LLM(
model=model_id,
dtype=torch.float16,
trust_remote_code=True,
quantization="bitblas",
max_model_len=1024
)
```
```python
from vllm import LLM
import torch
# "hxbgsyxh/llama-13b-4bit-g-1" is a pre-quantized checkpoint.
model_id = "hxbgsyxh/llama-13b-4bit-g-1"
llm = LLM(
model=model_id,
dtype=torch.float16,
trust_remote_code=True,
quantization="bitblas",
max_model_len=1024
)
```