ee0e5cc8d9
All gaudi values updated with extra flags. Added helm support for 2 new examples Text2Image and SearchQnA. Minor fix for llm-uservice. Signed-off-by: Dolpher Du <dolpher.du@intel.com>
37 lines
723 B
YAML
37 lines
723 B
YAML
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
vllm:
|
|
enabled: false
|
|
|
|
llm-uservice:
|
|
DOCSUM_BACKEND: "TGI"
|
|
|
|
tgi:
|
|
enabled: true
|
|
accelDevice: "gaudi"
|
|
image:
|
|
repository: ghcr.io/huggingface/tgi-gaudi
|
|
tag: "2.3.1"
|
|
resources:
|
|
limits:
|
|
habana.ai/gaudi: 1
|
|
CUDA_GRAPHS: ""
|
|
ENABLE_HPU_GRAPH: true
|
|
LIMIT_HPU_GRAPH: true
|
|
USE_FLASH_ATTENTION: true
|
|
FLASH_ATTENTION_RECOMPUTE: true
|
|
livenessProbe:
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 5
|
|
timeoutSeconds: 1
|
|
readinessProbe:
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 5
|
|
timeoutSeconds: 1
|
|
startupProbe:
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 5
|
|
timeoutSeconds: 1
|
|
failureThreshold: 120
|