Files
GenAIExamples/ChatQnA/kubernetes/helm/gaudi-tgi-values.yaml
dolpher ee0e5cc8d9 Sync value files from GenAIInfra (#1428)
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>
2025-01-22 17:44:11 +08:00

80 lines
2.0 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
# Accelerate inferencing in heaviest components to improve performance
# by overriding their subchart values
vllm:
enabled: false
# TGI: largest bottleneck for ChatQnA
tgi:
enabled: true
accelDevice: "gaudi"
image:
repository: ghcr.io/huggingface/tgi-gaudi
tag: "2.3.1"
resources:
limits:
habana.ai/gaudi: 1
# higher limits are needed with extra input tokens added by rerank
MAX_INPUT_LENGTH: "2048"
MAX_TOTAL_TOKENS: "4096"
CUDA_GRAPHS: ""
OMPI_MCA_btl_vader_single_copy_mechanism: "none"
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
# Reranking: second largest bottleneck when reranking is in use
# (i.e. query context docs have been uploaded with data-prep)
teirerank:
accelDevice: "gaudi"
OMPI_MCA_btl_vader_single_copy_mechanism: "none"
MAX_WARMUP_SEQUENCE_LENGTH: "512"
image:
repository: ghcr.io/huggingface/tei-gaudi
tag: 1.5.0
resources:
limits:
habana.ai/gaudi: 1
securityContext:
readOnlyRootFilesystem: false
livenessProbe:
timeoutSeconds: 1
readinessProbe:
timeoutSeconds: 1
# Embedding: Second largest bottleneck without rerank
# By default tei on gaudi is disabled.
# tei:
# accelDevice: "gaudi"
# OMPI_MCA_btl_vader_single_copy_mechanism: "none"
# MAX_WARMUP_SEQUENCE_LENGTH: "512"
# image:
# repository: ghcr.io/huggingface/tei-gaudi
# tag: 1.5.0
# resources:
# limits:
# habana.ai/gaudi: 1
# securityContext:
# readOnlyRootFilesystem: false
# livenessProbe:
# timeoutSeconds: 1
# readinessProbe:
# timeoutSeconds: 1