3694614dd9
Add experiments/dsv4_p800_max_context_length/ to find the longest input context that P800 SGLang INT8 can serve for DeepSeek-V4-Flash-INT8. - Docker-based server start with dynamic --context-length. - Single-request, single-output-token probes for each candidate length. - Records success/failure, server args, and metrics per length. - Generates results.json and report.md summarizing the max supported length. - Smoke-tested at 4096 tokens successfully.
44 lines
1.3 KiB
Bash
44 lines
1.3 KiB
Bash
# Common configuration for the max context length exploration on P800.
|
|
# All values can be overridden via environment variables.
|
|
|
|
EXPERIMENT="dsv4_p800_max_context_length"
|
|
MODEL_NAME="DeepSeek-V4-Flash-INT8"
|
|
MODEL_PATH="/data1/models/DeepSeek-V4-Flash-INT8"
|
|
SERVED_MODEL_NAME="deepseek-v4-flash-int8"
|
|
|
|
# Port must differ from other running experiments.
|
|
PORT="${PORT:-30013}"
|
|
|
|
# We want exact input lengths, so fix the random range ratio to 1.0.
|
|
OUTPUT_LEN="${OUTPUT_LEN:-1}"
|
|
NUM_PROMPTS="${NUM_PROMPTS:-1}"
|
|
MAX_CONCURRENCY="${MAX_CONCURRENCY:-1}"
|
|
REQUEST_RATE="${REQUEST_RATE:-10000}"
|
|
|
|
# Padding added to target length when setting server context length.
|
|
CONTEXT_PAD="${CONTEXT_PAD:-1024}"
|
|
|
|
# Candidate input lengths (tokens). Override via CANDIDATE_LENS env var.
|
|
# Examples:
|
|
# CANDIDATE_LENS="4096 8192 16384" bash run_bench.sh
|
|
# CANDIDATE_LENS=(4096 8192 16384) bash run_bench.sh
|
|
if [[ -z "${CANDIDATE_LENS:-}" ]]; then
|
|
declare -a CANDIDATE_LENS=(
|
|
4096
|
|
8192
|
|
16384
|
|
32768
|
|
65536
|
|
131072
|
|
262144
|
|
524288
|
|
)
|
|
elif ! declare -p CANDIDATE_LENS 2>/dev/null | grep -q '^declare -a'; then
|
|
# Normalize string-form arrays: remove surrounding parentheses and commas.
|
|
_CAND_STR="${CANDIDATE_LENS#(}"
|
|
_CAND_STR="${_CAND_STR%)}"
|
|
_CAND_STR="${_CAND_STR//,/}"
|
|
read -ra CANDIDATE_LENS <<< "$_CAND_STR"
|
|
unset _CAND_STR
|
|
fi
|