be94b8e7ef
- Add experiments/dsv4_p800_256k_4k_probe for testing 256k input + 4k output on DeepSeek-V4-Flash-INT8 with Kunlun P800. - Add SGLANG_EXTRA_LAUNCH_ARGS support to scripts/common/server_docker.sh so probe can inject --context-length 270000. - Add w8a8_int8_baseline server mode without EAGLE speculative decoding, matching the long-context P800 tuning. - Switch dsv4_p800_sglang and the new probe to use w8a8_int8_baseline by default; original tuned mode remains available via SERVER_MODE=w8a8_int8.
20 lines
686 B
Bash
Executable File
20 lines
686 B
Bash
Executable File
#!/usr/bin/env bash
|
|
set -Eeuo pipefail
|
|
|
|
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 "extra launch args: ${SGLANG_EXTRA_LAUNCH_ARGS:-<none>}"
|
|
|
|
docker_server_start "${MODEL_PATH}" "${PORT}" "${LOG_DIR}/server.outer.log" "${SERVER_MODE}" "${SGLANG_EXTRA_LAUNCH_ARGS:-}"
|