phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-02 20:40:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

completion() for tgi (#295)

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-10-24 16:02:41 -07:00 • committed by GitHub
parent cb84034567
commit 3e1c3fdb3f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 173 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/adapters/inference/vllm/vllm.py
View file

@ -143,7 +143,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
"model": VLLM_SUPPORTED_MODELS[request.model],
"prompt": chat_completion_request_to_prompt(request, self.formatter),
"stream": request.stream,
**get_sampling_options(request),
**get_sampling_options(request.sampling_params),
}
async def embeddings(