phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

revert: Fireworks chat completion broken due to telemetry (#3402)

Browse source 
Reverts llamastack/llama-stack#3392
This commit is contained in:
Francisco Arceo 2025-09-10 12:53:38 -06:00 • committed by GitHub
parent f6bf36343d
commit a6b1588dc6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/core/routers/inference.py
View file

@ -423,7 +423,7 @@ class InferenceRouter(Inference):
# response_stream = await provider.openai_completion(**params) # response_stream = await provider.openai_completion(**params)
response = await provider.openai_completion(**params) response = await provider.openai_completion(**params)
if self.telemetry and getattr(response, "usage", None): if self.telemetry:
metrics = self._construct_metrics( metrics = self._construct_metrics(
prompt_tokens=response.usage.prompt_tokens, prompt_tokens=response.usage.prompt_tokens,
completion_tokens=response.usage.completion_tokens, completion_tokens=response.usage.completion_tokens,
@ -529,7 +529,7 @@ class InferenceRouter(Inference):
if self.store: if self.store:
asyncio.create_task(self.store.store_chat_completion(response, messages)) asyncio.create_task(self.store.store_chat_completion(response, messages))
if self.telemetry and getattr(response, "usage", None): if self.telemetry:
metrics = self._construct_metrics( metrics = self._construct_metrics(
prompt_tokens=response.usage.prompt_tokens, prompt_tokens=response.usage.prompt_tokens,
completion_tokens=response.usage.completion_tokens, completion_tokens=response.usage.completion_tokens,