phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix: Revert "feat: record token usage for inference API (#1300)" (#1476)

Browse source 
This reverts commit b8535417e0.

Test plan:
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run
~/.llama/distributions/together/together-run.yaml
python -m examples.agents.e2e_loop_with_client_tools localhost 8321
This commit is contained in:
Dinesh Yeduguru 2025-03-07 10:16:47 -08:00 • committed by GitHub
parent df4fbae35c
commit 60e7f3d705
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 14 additions and 161 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/distribution/resolver.py
View file

@ -163,9 +163,7 @@ def specs_for_autorouted_apis(apis_to_serve: List[str] | Set[str]) -> Dict[str,
module="llama_stack.distribution.routers",
routing_table_api=info.routing_table_api,
api_dependencies=[info.routing_table_api],
# Add telemetry as an optional dependency to all auto-routed providers
optional_api_dependencies=[Api.telemetry],
deps__=([info.routing_table_api.value, Api.telemetry.value]),
deps__=[info.routing_table_api.value],
),
)
}