Skip to content

perf: attestation optimizations + persistent GPU worker + e2e benchmarks #70

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Evrard-Nil merged 7 commits into from
Mar 24, 2026
Merged

perf: attestation optimizations + persistent GPU worker + e2e benchmarks #70

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
a65ea69
fix: update aws-lc-sys and rustls-webpki to resolve security vulnerab…
Evrard-Nil Mar 23, 2026
9d067c3
perf: parallelize attestation and add e2e benchmarks
Evrard-Nil Mar 23, 2026
382845c
perf: persistent Python worker for GPU evidence collection
Evrard-Nil Mar 23, 2026
059114d
style: cargo fmt
Evrard-Nil Mar 23, 2026
d234903
add live endpoint benchmark script
Evrard-Nil Mar 23, 2026
acb3691
fix: redirect stdout in GPU evidence worker to prevent protocol corru…
Evrard-Nil Mar 23, 2026
0ebf876
perf: cache serialized bytes, narrow GPU semaphore, remove double ser…
Evrard-Nil Mar 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
/target
.GIT_REV
oci.tar
.DS_Store
14 changes: 8 additions & 6 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

6 changes: 5 additions & 1 deletion Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,8 +57,12 @@ metrics-exporter-prometheus = "0.18"
[dev-dependencies]
wiremock = "0.6"
tower = { version = "0.5", features = ["util"] }
criterion = { version = "0.5", features = ["html_reports"] }
criterion = { version = "0.5", features = ["html_reports", "async_tokio"] }

[[bench]]
name = "hot_path"
harness = false

[[bench]]
name = "e2e"
harness = false
5 changes: 3 additions & 2 deletions Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ ENV SOURCE_DATE_EPOCH=${SOURCE_DATE_EPOCH}
# Cache dependencies: copy manifests first, then do a dummy build
COPY Cargo.toml Cargo.lock ./
RUN mkdir src && echo "fn main() {}" > src/main.rs && echo "" > src/lib.rs \
&& mkdir -p benches && echo "fn main() {}" > benches/hot_path.rs \
&& mkdir -p benches && echo "fn main() {}" > benches/hot_path.rs && echo "fn main() {}" > benches/e2e.rs \
&& cargo build --release --locked 2>/dev/null || true \
&& rm -rf src benches \
&& rm -f target/release/deps/*vllm_proxy_rs* \
Expand All @@ -37,8 +37,9 @@ RUN pip install --no-cache-dir nv-attestation-sdk nv-ppcie-verifier

WORKDIR /app

# Copy compiled binary from builder
# Copy compiled binary and GPU evidence worker from builder
COPY --from=builder /build/target/release/vllm-proxy-rs /app/vllm-proxy-rs
COPY gpu_evidence_worker.py /app/gpu_evidence_worker.py

# Bake in git revision for version tracking
COPY --chmod=664 .GIT_REV /etc/
Expand Down
Loading
Loading