efort
/
glm4
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'main' of https://github.com/THUDM/GLM-4

This commit is contained in:
zR 2024-11-18 11:51:56 +08:00
parent 804733811f b052da77b1
commit 4c66fa48d1
1 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
basic_demo/vllm_cli_vision_demo.py
View File

@ -46,9 +46,6 @@ async def vllm_gen(messages: List[Dict[str, str]], top_p: float, temperature: fl
"temperature": temperature,
"top_p": top_p,
"top_k": -1,
"use_beam_search": False,
"length_penalty": 1,
"early_stopping": False,
"ignore_eos": False,
"max_tokens": max_dec_len,
"logprobs": None,
@ -58,7 +55,7 @@ async def vllm_gen(messages: List[Dict[str, str]], top_p: float, temperature: fl
}
sampling_params = SamplingParams(**params_dict)
async for output in engine.generate(inputs=inputs, sampling_params=sampling_params, request_id=f"{time.time()}"):
async for output in engine.generate(prompt=inputs, sampling_params=sampling_params, request_id=f"{time.time()}"):
yield output.outputs[0].text