phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-16 18:08:09 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Rename all inline providers with an inline:: prefix (#423)

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-11 22:19:16 -08:00 • committed by GitHub
parent f4426f6a43
commit 3d7561e55c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 63 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

10
distributions/meta-reference-quantized-gpu/run.yaml
View file

@ -14,7 +14,7 @@ apis:
providers:
inference:
- provider_id: meta0
provider_type: meta-reference-quantized
provider_type: inline::meta-reference-quantized
config:
model: Llama3.2-3B-Instruct:int4-qlora-eo8
quantization:
@ -23,7 +23,7 @@ providers:
max_seq_len: 2048
max_batch_size: 1
- provider_id: meta1
provider_type: meta-reference-quantized
provider_type: inline::meta-reference-quantized
config:
# not a quantized model !
model: Llama-Guard-3-1B
@ -43,11 +43,11 @@ providers:
model: Prompt-Guard-86M
memory:
- provider_id: meta0
provider_type: meta-reference
provider_type: inline::meta-reference
config: {}
agents:
- provider_id: meta0
provider_type: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
namespace: null
@ -55,5 +55,5 @@ providers:
db_path: ~/.llama/runtime/kvstore.db
telemetry:
- provider_id: meta0
provider_type: meta-reference
provider_type: inline::meta-reference
config: {}