phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 07:33:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'refs/heads/main' into preprocessors

Browse source 
# Conflicts:
#	llama_stack/distribution/routers/routers.py
#	llama_stack/templates/ollama/build.yaml
#	llama_stack/templates/ollama/run-with-safety.yaml
#	llama_stack/templates/ollama/run.yaml
#	llama_stack/templates/remote-vllm/build.yaml
#	llama_stack/templates/remote-vllm/run-with-safety.yaml
#	llama_stack/templates/remote-vllm/run.yaml
#	llama_stack/templates/together/build.yaml
#	llama_stack/templates/together/run-with-safety.yaml
#	llama_stack/templates/together/run.yaml
This commit is contained in:
ilya-kolchinsky 2025-03-07 16:20:30 +01:00
commit 6b9f673fdb
313 changed files with 181388 additions and 7064 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/templates/tgi/tgi.py
View file

@ -57,7 +57,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
inference_model = ModelInput(
@ -151,7 +151,7 @@ def get_distribution_template() -> DistributionTemplate:
"Inference model loaded into the TGI server",
),
"TGI_URL": (
"http://127.0.0.1:8080}/v1",
"http://127.0.0.1:8080/v1",
"URL of the TGI server with the main inference model",
),
"TGI_SAFETY_URL": (