phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-30 09:24:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into feat/litellm_sambanova_usage

Browse source
This commit is contained in:
Jorge Piedrahita Ortiz 2025-03-24 08:02:40 -05:00 • committed by GitHub
commit 8783dd8162
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
190 changed files with 8649 additions and 3304 deletions
Download patch file Download diff file Expand all files Collapse all files

57
distributions/dependencies.json
View file

@ -7,10 +7,12 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -23,6 +25,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -41,10 +44,12 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"nltk",
"numpy",
@ -56,6 +61,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -75,10 +81,12 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fastapi",
"fire",
"fireworks-ai",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -91,6 +99,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -112,11 +121,13 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"langdetect",
"matplotlib",
"nltk",
"numpy",
@ -128,6 +139,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -147,10 +159,12 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fastapi",
"fire",
"fireworks-ai",
"httpx",
"langdetect",
"litellm",
"matplotlib",
"mcp",
@ -164,6 +178,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -184,11 +199,13 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"fireworks-ai",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -201,6 +218,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -219,10 +237,12 @@
"blobfile",
"chardet",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"litellm",
"matplotlib",
"nltk",
@ -235,6 +255,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -253,11 +274,13 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -270,6 +293,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -288,11 +312,13 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -305,6 +331,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -325,11 +352,13 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fairscale",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"lm-format-enforcer",
"matplotlib",
"mcp",
@ -343,6 +372,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -365,12 +395,14 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fairscale",
"faiss-cpu",
"fastapi",
"fbgemm-gpu",
"fire",
"httpx",
"langdetect",
"lm-format-enforcer",
"matplotlib",
"mcp",
@ -384,6 +416,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -403,10 +436,12 @@
"aiosqlite",
"blobfile",
"chardet",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"nltk",
"numpy",
@ -418,6 +453,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -436,10 +472,12 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -453,6 +491,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -470,9 +509,11 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fastapi",
"fire",
"httpx",
"langdetect",
"litellm",
"matplotlib",
"mcp",
@ -486,6 +527,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -505,10 +547,12 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -521,6 +565,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -540,10 +585,12 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -556,6 +603,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -608,11 +656,13 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -625,6 +675,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -644,10 +695,12 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -660,6 +713,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
@ -680,10 +734,12 @@
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
@ -696,6 +752,7 @@
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",

4
distributions/ollama/compose.yaml
View file

@ -51,14 +51,14 @@ services:
- ~/local/llama-stack/:/app/llama-stack-source
- ./run${SAFETY_MODEL:+-with-safety}.yaml:/root/my-run.yaml
ports:
- "${LLAMA_STACK_PORT:-5001}:${LLAMA_STACK_PORT:-5001}"
- "${LLAMA_STACK_PORT:-8321}:${LLAMA_STACK_PORT:-8321}"
environment:
- INFERENCE_MODEL=${INFERENCE_MODEL}
- SAFETY_MODEL=${SAFETY_MODEL:-}
- OLLAMA_URL=http://ollama:11434
entrypoint: >
python -m llama_stack.distribution.server.server /root/my-run.yaml \
--port ${LLAMA_STACK_PORT:-5001}
--port ${LLAMA_STACK_PORT:-8321}
deploy:
restart_policy:
condition: on-failure

BIN
distributions/ramalama/faiss_store.db Normal file
View file

Binary file not shown.

4
distributions/remote-vllm/compose.yaml
View file

@ -84,9 +84,9 @@ services:
- SQLITE_STORE_DIR=${SQLITE_STORE_DIR:-$HOME/.llama/distributions/remote-vllm}
- SAFETY_MODEL=${SAFETY_MODEL:-meta-llama/Llama-Guard-3-1B}
ports:
- "${LLAMA_STACK_PORT:-5001}:${LLAMA_STACK_PORT:-5001}"
- "${LLAMA_STACK_PORT:-8321}:${LLAMA_STACK_PORT:-8321}"
# Hack: wait for vLLM server to start before starting docker
entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-remote-vllm.yaml --port 5001"
entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-remote-vllm.yaml --port 8321"
deploy:
restart_policy:
condition: on-failure

2
distributions/tgi/compose.yaml
View file

@ -83,7 +83,7 @@ services:
- ~/.llama:/root/.llama
- ./run${TGI_SAFETY_MODEL:+-with-safety}.yaml:/root/my-run.yaml
ports:
- "${LLAMA_STACK_PORT:-5001}:${LLAMA_STACK_PORT:-5001}"
- "${LLAMA_STACK_PORT:-8321}:${LLAMA_STACK_PORT:-8321}"
# Hack: wait for TGI server to start before starting docker
entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
restart_policy: