phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: OAI compat endpoint for meta reference inference provider (#1962)

Browse source 
Test plan:
python tests/verifications/generate_report.py --providers
fireworks,together,llama_meta_ref,openai

Co-authored-by: Eric Huang <erichuang@fb.com>
This commit is contained in:
ehhuang 2025-04-17 11:16:04 -07:00 • committed by GitHub
parent 8bd6665775
commit 2976b5d992
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 1184 additions and 44 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -515,7 +515,8 @@ class MetaReferenceInferenceImpl(
stop_reason = None
ipython = False
for token_result in self.generator.chat_completion(request):
for token_results in self.generator.chat_completion([request]):
token_result = token_results[0]
if os.environ.get("LLAMA_MODELS_DEBUG", "0") == "1":
cprint(token_result.text, "cyan", end="")
if os.environ.get("LLAMA_MODELS_DEBUG", "0") == "2":