f6a45f1ed8
- Add experiments/dsv4_p800_long_context_matrix for 64k/128k/256k context grid on DeepSeek-V4-Flash-INT8 with Kunlun P800. - Change bench_client_docker.sh to use --concurrency instead of --max-concurrency to match the user's long-context benchmark script. - Add SGLANG_HEALTH_CHECK_TIMEOUT override to server_docker.sh for slow long-context server startups. - Tune dsv4_p800_256k_4k_probe with lower max-running-requests and mem-fraction-static to avoid OOM on P800.
29 lines
1.0 KiB
Bash
Executable File
29 lines
1.0 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 "$SCRIPT_DIR")"
|
|
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/../../scripts/common/server_docker.sh"
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/config.env"
|
|
|
|
log_init "${RESULT_ROOT:-/tmp/${EXPERIMENT_NAME}}/logs/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}"
|