llama-stack-mirror/llama_stack
ehhuang 29072f40ab
feat: new system prompt for llama4 (#2031)
Tests:

LLAMA_STACK_CONFIG=http://localhost:5002 pytest -s -v
tests/integration/inference --safety-shield meta-llama/Llama-Guard-3-8B
--vision-model meta-llama/Llama-4-Scout-17B-16E-Instruct --text-model
meta-llama/Llama-4-Scout-17B-16E-Instruct

Co-authored-by: Eric Huang <erichuang@fb.com>
2025-04-25 11:29:08 -07:00
..
apis feat(agents): add agent naming functionality (#1922) 2025-04-17 07:02:47 -07:00
cli feat(cli): add interactive tab completion for image type selection (#2027) 2025-04-25 16:57:42 +02:00
distribution fix: add endpoint route debugs 2025-04-25 10:40:12 -07:00
models feat: new system prompt for llama4 (#2031) 2025-04-25 11:29:08 -07:00
providers feat: new system prompt for llama4 (#2031) 2025-04-25 11:29:08 -07:00
strong_typing chore: more mypy checks (ollama, vllm, ...) (#1777) 2025-04-01 17:12:39 +02:00
templates feat: NVIDIA allow non-llama model registration (#1859) 2025-04-24 17:13:33 -07:00
__init__.py export LibraryClient 2024-12-13 12:08:00 -08:00
env.py refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401) 2025-03-04 14:53:47 -08:00
log.py chore: Remove style tags from log formatter (#1808) 2025-03-27 10:18:21 -04:00
schema_utils.py fix: dont check protocol compliance for experimental methods 2025-04-12 16:26:32 -07:00