sglangv0.5.2 & support Qwen3-Next-80B-A3B-Instruct
This commit is contained in:
maxiao1
306
.github/workflows/pr-benchmark-rust.yml
vendored
Normal file
306
.github/workflows/pr-benchmark-rust.yml
vendored
Normal file
@@ -0,0 +1,306 @@
|
||||
name: PR Benchmark (Rust Router)
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ main ]
|
||||
paths:
|
||||
- "sgl-router/**"
|
||||
pull_request:
|
||||
branches: [ main ]
|
||||
paths:
|
||||
- "sgl-router/**"
|
||||
types: [opened, synchronize, reopened, labeled]
|
||||
workflow_dispatch:
|
||||
|
||||
concurrency:
|
||||
group: pr-benchmark-rust-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: write
|
||||
issues: write
|
||||
jobs:
|
||||
# Quick check job that always runs on PRs
|
||||
benchmark-compile-check:
|
||||
name: Benchmark Compilation Check
|
||||
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
bash scripts/ci/ci_install_rust.sh
|
||||
|
||||
- name: Setup sccache
|
||||
uses: mozilla-actions/sccache-action@v0.0.3
|
||||
continue-on-error: true
|
||||
|
||||
- name: Rust cache
|
||||
uses: Swatinem/rust-cache@v2
|
||||
with:
|
||||
workspaces: sgl-router
|
||||
# Share cache across all benchmark jobs
|
||||
shared-key: "rust-cache"
|
||||
# Save cache even on failure
|
||||
save-if: true
|
||||
|
||||
- name: Check benchmarks compile
|
||||
run: |
|
||||
source "$HOME/.cargo/env"
|
||||
cd sgl-router/
|
||||
# Try to use sccache, but disable if it fails
|
||||
if command -v sccache &> /dev/null; then
|
||||
echo "Testing sccache availability..."
|
||||
# Try to start sccache and check if it works
|
||||
export RUSTC_WRAPPER=sccache
|
||||
export SCCACHE_GHA_ENABLED="true"
|
||||
if sccache --start-server 2>/dev/null && sccache --show-stats 2>/dev/null; then
|
||||
echo "sccache is working, using it for compilation"
|
||||
else
|
||||
echo "sccache failed to start, falling back to regular cargo"
|
||||
unset RUSTC_WRAPPER
|
||||
unset SCCACHE_GHA_ENABLED
|
||||
fi
|
||||
else
|
||||
echo "sccache not available, using regular cargo"
|
||||
fi
|
||||
cargo check --benches
|
||||
|
||||
# Full benchmark jobs that only run with label or on main branch
|
||||
benchmark-request-processing:
|
||||
name: Request Processing Benchmark
|
||||
if: |
|
||||
github.repository == 'sgl-project/sglang' &&
|
||||
(github.event_name == 'push' ||
|
||||
github.event_name == 'workflow_dispatch' ||
|
||||
contains(github.event.pull_request.labels.*.name, 'benchmark'))
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
# Fetch enough history for baseline comparison
|
||||
fetch-depth: 100
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
bash scripts/ci/ci_install_rust.sh
|
||||
|
||||
- name: Setup sccache
|
||||
uses: mozilla-actions/sccache-action@v0.0.3
|
||||
continue-on-error: true
|
||||
|
||||
- name: Rust cache
|
||||
uses: Swatinem/rust-cache@v2
|
||||
with:
|
||||
workspaces: sgl-router
|
||||
# Share cache across all benchmark jobs
|
||||
shared-key: "rust-cache"
|
||||
# Save cache even on failure
|
||||
save-if: true
|
||||
|
||||
- name: Run request processing benchmark
|
||||
timeout-minutes: 30
|
||||
run: |
|
||||
source "$HOME/.cargo/env"
|
||||
cd sgl-router/
|
||||
# Try to use sccache, but disable if it fails
|
||||
if command -v sccache &> /dev/null; then
|
||||
echo "Testing sccache availability..."
|
||||
# Try to start sccache and check if it works
|
||||
export RUSTC_WRAPPER=sccache
|
||||
export SCCACHE_GHA_ENABLED="true"
|
||||
if sccache --start-server 2>/dev/null && sccache --show-stats 2>/dev/null; then
|
||||
echo "sccache is working, using it for compilation"
|
||||
else
|
||||
echo "sccache failed to start, falling back to regular cargo"
|
||||
unset RUSTC_WRAPPER
|
||||
unset SCCACHE_GHA_ENABLED
|
||||
fi
|
||||
else
|
||||
echo "sccache not available, using regular cargo"
|
||||
fi
|
||||
# Run only the summary benchmark for quick validation in PRs
|
||||
cargo bench --bench request_processing -- benchmark_summary --exact
|
||||
|
||||
- name: Upload benchmark results
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: request-processing-results-${{ github.sha }}
|
||||
path: |
|
||||
sgl-router/target/criterion/benchmark_summary/
|
||||
retention-days: 30
|
||||
|
||||
benchmark-tokenizer:
|
||||
name: Tokenizer Benchmark
|
||||
if: |
|
||||
github.repository == 'sgl-project/sglang' &&
|
||||
(github.event_name == 'push' ||
|
||||
github.event_name == 'workflow_dispatch' ||
|
||||
contains(github.event.pull_request.labels.*.name, 'benchmark'))
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 100
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
bash scripts/ci/ci_install_rust.sh
|
||||
|
||||
- name: Setup sccache
|
||||
uses: mozilla-actions/sccache-action@v0.0.3
|
||||
continue-on-error: true
|
||||
|
||||
- name: Rust cache
|
||||
uses: Swatinem/rust-cache@v2
|
||||
with:
|
||||
workspaces: sgl-router
|
||||
# Share cache across all benchmark jobs
|
||||
shared-key: "rust-cache"
|
||||
# Save cache even on failure
|
||||
save-if: true
|
||||
|
||||
- name: Run tokenizer benchmark
|
||||
timeout-minutes: 30
|
||||
run: |
|
||||
source "$HOME/.cargo/env"
|
||||
cd sgl-router/
|
||||
# Try to use sccache, but disable if it fails
|
||||
if command -v sccache &> /dev/null; then
|
||||
echo "Testing sccache availability..."
|
||||
# Try to start sccache and check if it works
|
||||
export RUSTC_WRAPPER=sccache
|
||||
export SCCACHE_GHA_ENABLED="true"
|
||||
if sccache --start-server 2>/dev/null && sccache --show-stats 2>/dev/null; then
|
||||
echo "sccache is working, using it for compilation"
|
||||
else
|
||||
echo "sccache failed to start, falling back to regular cargo"
|
||||
unset RUSTC_WRAPPER
|
||||
unset SCCACHE_GHA_ENABLED
|
||||
fi
|
||||
else
|
||||
echo "sccache not available, using regular cargo"
|
||||
fi
|
||||
cargo bench --bench tokenizer_benchmark
|
||||
|
||||
- name: Upload benchmark results
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: tokenizer-results-${{ github.sha }}
|
||||
path: |
|
||||
sgl-router/target/criterion/tokenizer*/
|
||||
retention-days: 30
|
||||
|
||||
benchmark-tool-parser:
|
||||
name: Tool Parser Benchmark
|
||||
if: |
|
||||
github.repository == 'sgl-project/sglang' &&
|
||||
(github.event_name == 'push' ||
|
||||
github.event_name == 'workflow_dispatch' ||
|
||||
contains(github.event.pull_request.labels.*.name, 'benchmark'))
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 100
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
bash scripts/ci/ci_install_rust.sh
|
||||
|
||||
- name: Setup sccache
|
||||
uses: mozilla-actions/sccache-action@v0.0.3
|
||||
continue-on-error: true
|
||||
|
||||
- name: Rust cache
|
||||
uses: Swatinem/rust-cache@v2
|
||||
with:
|
||||
workspaces: sgl-router
|
||||
# Share cache across all benchmark jobs
|
||||
shared-key: "rust-cache"
|
||||
# Save cache even on failure
|
||||
save-if: true
|
||||
|
||||
- name: Run tool parser benchmark
|
||||
timeout-minutes: 30
|
||||
run: |
|
||||
source "$HOME/.cargo/env"
|
||||
cd sgl-router/
|
||||
# Try to use sccache, but disable if it fails
|
||||
if command -v sccache &> /dev/null; then
|
||||
echo "Testing sccache availability..."
|
||||
# Try to start sccache and check if it works
|
||||
export RUSTC_WRAPPER=sccache
|
||||
export SCCACHE_GHA_ENABLED="true"
|
||||
if sccache --start-server 2>/dev/null && sccache --show-stats 2>/dev/null; then
|
||||
echo "sccache is working, using it for compilation"
|
||||
else
|
||||
echo "sccache failed to start, falling back to regular cargo"
|
||||
unset RUSTC_WRAPPER
|
||||
unset SCCACHE_GHA_ENABLED
|
||||
fi
|
||||
else
|
||||
echo "sccache not available, using regular cargo"
|
||||
fi
|
||||
cargo bench --bench tool_parser_benchmark
|
||||
|
||||
- name: Upload benchmark results
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: tool-parser-results-${{ github.sha }}
|
||||
path: |
|
||||
sgl-router/target/criterion/tool_parser*/
|
||||
retention-days: 30
|
||||
|
||||
benchmark-summary:
|
||||
name: Benchmark Summary
|
||||
needs: [benchmark-request-processing, benchmark-tokenizer, benchmark-tool-parser]
|
||||
if: always() && (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request')
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Download all benchmark results
|
||||
uses: actions/download-artifact@v4
|
||||
with:
|
||||
pattern: '*-results-${{ github.sha }}'
|
||||
path: benchmark-results
|
||||
|
||||
- name: Generate summary
|
||||
run: |
|
||||
echo "## Benchmark Results Summary" > summary.md
|
||||
echo "" >> summary.md
|
||||
echo "### Request Processing" >> summary.md
|
||||
if [ -d "benchmark-results/request-processing-results-${{ github.sha }}" ]; then
|
||||
echo "✅ Completed" >> summary.md
|
||||
else
|
||||
echo "❌ Failed or skipped" >> summary.md
|
||||
fi
|
||||
echo "" >> summary.md
|
||||
echo "### Tokenizer" >> summary.md
|
||||
if [ -d "benchmark-results/tokenizer-results-${{ github.sha }}" ]; then
|
||||
echo "✅ Completed" >> summary.md
|
||||
else
|
||||
echo "❌ Failed or skipped" >> summary.md
|
||||
fi
|
||||
echo "" >> summary.md
|
||||
echo "### Tool Parser" >> summary.md
|
||||
if [ -d "benchmark-results/tool-parser-results-${{ github.sha }}" ]; then
|
||||
echo "✅ Completed" >> summary.md
|
||||
else
|
||||
echo "❌ Failed or skipped" >> summary.md
|
||||
fi
|
||||
cat summary.md
|
||||
|
||||
- name: Upload summary
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: benchmark-summary-${{ github.sha }}
|
||||
path: summary.md
|
||||
retention-days: 30
|
||||
Reference in New Issue
Block a user