phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 17:29:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Redo code change after merge

Browse source
This commit is contained in:
Fred Reiss 2024-12-19 11:35:25 -08:00
parent 3de586aed4
commit 6ec9eabbeb
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -169,7 +169,8 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
log.info("Sampling params: %s", sampling_params) log.info("Sampling params: %s", sampling_params)
request_id = _random_uuid() request_id = _random_uuid()
prompt = await chat_completion_request_to_prompt(request, self.formatter) prompt = await chat_completion_request_to_prompt(request, self.config.model,
self.formatter)
vllm_sampling_params = self._sampling_params(request.sampling_params) vllm_sampling_params = self._sampling_params(request.sampling_params)
results_generator = self.engine.generate( results_generator = self.engine.generate(
prompt, vllm_sampling_params, request_id prompt, vllm_sampling_params, request_id