phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 09:02:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: kill inline::vllm

Browse source
This commit is contained in:
Ashwin Bharambe 2025-07-18 15:45:39 -07:00
parent 68a2dfbad7
commit 5650e1fa09
12 changed files with 0 additions and 1388 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/registry/inference.py
View file

@ -37,16 +37,6 @@ def available_providers() -> list[ProviderSpec]:
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
description="Meta's reference implementation of inference with support for various model formats and optimization techniques.",
),
InlineProviderSpec(
api=Api.inference,
provider_type="inline::vllm",
pip_packages=[
"vllm",
],
module="llama_stack.providers.inline.inference.vllm",
config_class="llama_stack.providers.inline.inference.vllm.VLLMConfig",
description="vLLM inference provider for high-performance model serving with PagedAttention and continuous batching.",
),
InlineProviderSpec(
api=Api.inference,
provider_type="inline::sentence-transformers",