Mirrors/criu
1
0
Fork 0
mirror of https://github.com/checkpoint-restore/criu.git synced 2026-07-17 16:47:50 +00:00
Code Issues Projects Releases Wiki Activity
criu/contrib/compression-benchmark
History
Exact
Radostin Stoyanov 2d1335b755 contrib: Benchmark vLLM compression 
Serving engines have different memory layouts and restore behavior, so
SGLang results do not establish the cost or correctness of compression
for vLLM.

Add a vLLM frontend to the shared Podman benchmark. Support CPU and GPU
images and the supported server entrypoint forms, compare uncompressed,
per-page LZ4, and region LZ4 images, and verify deterministic inference
after restore. Report archive, checkpoint, restore, and post-restore
request costs, and add a bounded CPU test runner.

Reuse the shared runc.conf transaction, CRIU configuration isolation,
inventory validation, secret redaction, failure diagnostics, and
cleanup semantics so both serving benchmarks follow the same
methodology.

Assisted-by: Codex:GPT-5
Assisted-by: Claude:claude-fable-5
Signed-off-by: Radostin Stoyanov <rstoyanov@fedoraproject.org>
2026-07-14 10:17:01 +01:00
..
main.py
podman-sglang.py contrib: Benchmark SGLang compression 2026-07-14 10:17:01 +01:00
podman-vllm.py contrib: Benchmark vLLM compression 2026-07-14 10:17:01 +01:00
podman_common.py contrib: Benchmark SGLang compression 2026-07-14 10:17:01 +01:00
region-cache.py
workload.py