xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-23 16:14:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix] Update python to python3 calls for image; fix prefix & input calculations. (#21391)

Browse Source 
Signed-off-by: Eric Hanley <ericehanley@google.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
ericehanley 2025-07-22 22:33:00 -05:00 committed by GitHub
parent f154bb9ff0
commit 4f76a05f4f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
benchmarks/auto_tune/auto_tune.sh
View File

@ -126,11 +126,12 @@ run_benchmark() {
# get a basic qps by using request-rate inf
bm_log="$LOG_FOLDER/bm_log_${max_num_seqs}_${max_num_batched_tokens}_requestrate_inf.txt"
prefix_len=$(( INPUT_LEN * MIN_CACHE_HIT_PCT / 100 ))
python benchmarks/benchmark_serving.py \
adjusted_input_len=$(( INPUT_LEN - prefix_len ))
python3 benchmarks/benchmark_serving.py \
--backend vllm \
--model $MODEL \
--dataset-name random \
--random-input-len $INPUT_LEN \
--random-input-len $adjusted_input_len \
--random-output-len $OUTPUT_LEN \
--ignore-eos \
--disable-tqdm \
@ -159,11 +160,11 @@ run_benchmark() {
curl -X POST http://0.0.0.0:8004/reset_prefix_cache
sleep 5
bm_log="$LOG_FOLDER/bm_log_${max_num_seqs}_${max_num_batched_tokens}_requestrate_${request_rate}.txt"
python benchmarks/benchmark_serving.py \
python3 benchmarks/benchmark_serving.py \
--backend vllm \
--model $MODEL \
--dataset-name random \
--random-input-len $INPUT_LEN \
--random-input-len $adjusted_input_len \
--random-output-len $OUTPUT_LEN \
--ignore-eos \
--disable-tqdm \