phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 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/fireworks/fireworks.py
View file

@ -116,7 +116,7 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference):
if prompt.startswith("<|begin_of_text|>"):
prompt = prompt[len("<|begin_of_text|>") :]
options = get_sampling_options(request)
options = get_sampling_options(request.sampling_params)
options.setdefault("max_tokens", 512)
if fmt := request.response_format: