- Fix LOG_DIR unbound variable in long-context matrix start_server.sh. - Add BKCL RDMA env vars to w8a8_int8_baseline mode so cross-device communication initializes correctly (was missing BKCL_RDMA_NICS).
31 lines
1.1 KiB
Bash
Executable File
31 lines
1.1 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Start SGLang server for the P800 long-context matrix.
|
|
# Usage: start_server.sh <context_length> <max_running>
|
|
set -Eeuo pipefail
|
|
|
|
CONTEXT_LENGTH="${1:-80000}"
|
|
MAX_RUNNING="${2:-64}"
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"
|
|
RESULT_ROOT="${RESULT_ROOT:-/tmp/${EXPERIMENT_NAME}}"
|
|
LOG_DIR="${RESULT_ROOT}/logs"
|
|
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/../../scripts/common/server_docker.sh"
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/config.env"
|
|
|
|
log_init "${LOG_DIR}/start_server.log"
|
|
log "starting server for ${EXPERIMENT_NAME}"
|
|
log "model: ${MODEL_PATH}"
|
|
log "port: ${PORT}"
|
|
log "server mode: ${SERVER_MODE}"
|
|
log "context length: ${CONTEXT_LENGTH}"
|
|
log "max running requests: ${MAX_RUNNING}"
|
|
|
|
extra_args="--context-length ${CONTEXT_LENGTH} --max-running-requests ${MAX_RUNNING} --mem-fraction-static 0.85"
|
|
export SGLANG_EXTRA_LAUNCH_ARGS="${SGLANG_EXTRA_LAUNCH_ARGS:-${extra_args}}"
|
|
|
|
docker_server_start "${MODEL_PATH}" "${PORT}" "${LOG_DIR}/server.outer.log" "${SERVER_MODE}" "${SGLANG_EXTRA_LAUNCH_ARGS}"
|