1ff85f6a85
Signed-off-by: lvliang-intel <liang1.lv@intel.com> Co-authored-by: chen, suyue <suyue.chen@intel.com>
31 lines
944 B
YAML
31 lines
944 B
YAML
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
services:
|
|
tgi-server:
|
|
image: ghcr.io/huggingface/tgi-gaudi:2.0.6
|
|
container_name: tgi-server
|
|
ports:
|
|
- "8085:80"
|
|
volumes:
|
|
- ${HF_CACHE_DIR}:/data
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
HF_HUB_DISABLE_PROGRESS_BARS: 1
|
|
HF_HUB_ENABLE_HF_TRANSFER: 0
|
|
HABANA_VISIBLE_DEVICES: all
|
|
OMPI_MCA_btl_vader_single_copy_mechanism: none
|
|
PT_HPU_ENABLE_LAZY_COLLECTIVES: true
|
|
ENABLE_HPU_GRAPH: true
|
|
LIMIT_HPU_GRAPH: true
|
|
USE_FLASH_ATTENTION: true
|
|
FLASH_ATTENTION_RECOMPUTE: true
|
|
runtime: habana
|
|
cap_add:
|
|
- SYS_NICE
|
|
ipc: host
|
|
command: --model-id ${LLM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192 --sharded true --num-shard ${NUM_SHARDS}
|