Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
change
sglang
Commits
2c7f01bc
Unverified
Commit
2c7f01bc
authored
Aug 10, 2025
by
Lianmin Zheng
Committed by
GitHub
Aug 10, 2025
Browse files
Reorganize CI and test files (#9027)
parent
b58ae7a2
Changes
66
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
87 additions
and
88 deletions
+87
-88
.github/workflows/execute-notebook.yml
.github/workflows/execute-notebook.yml
+1
-1
.github/workflows/experiment-runner.yml
.github/workflows/experiment-runner.yml
+1
-1
.github/workflows/nightly-test-amd.yml
.github/workflows/nightly-test-amd.yml
+3
-3
.github/workflows/nightly-test.yml
.github/workflows/nightly-test.yml
+1
-1
.github/workflows/pr-benchmark-rust.yml
.github/workflows/pr-benchmark-rust.yml
+2
-2
.github/workflows/pr-test-amd.yml
.github/workflows/pr-test-amd.yml
+42
-42
.github/workflows/pr-test-npu.yml
.github/workflows/pr-test-npu.yml
+3
-3
.github/workflows/pr-test-pd-router.yml
.github/workflows/pr-test-pd-router.yml
+4
-4
.github/workflows/pr-test-rust.yml
.github/workflows/pr-test-rust.yml
+2
-2
.github/workflows/pr-test-sgl-kernel.yml
.github/workflows/pr-test-sgl-kernel.yml
+2
-2
.github/workflows/pr-test.yml
.github/workflows/pr-test.yml
+13
-13
.github/workflows/release-docs.yml
.github/workflows/release-docs.yml
+8
-9
.github/workflows/vllm-dependency-test.yml
.github/workflows/vllm-dependency-test.yml
+1
-1
README.md
README.md
+1
-1
scripts/ci/amd_ci_exec.sh
scripts/ci/amd_ci_exec.sh
+0
-0
scripts/ci/amd_ci_install_dependency.sh
scripts/ci/amd_ci_install_dependency.sh
+0
-0
scripts/ci/amd_ci_start_container.sh
scripts/ci/amd_ci_start_container.sh
+1
-1
scripts/ci/ci_install_deepep.sh
scripts/ci/ci_install_deepep.sh
+1
-1
scripts/ci/ci_install_dependency.sh
scripts/ci/ci_install_dependency.sh
+1
-1
scripts/ci/ci_install_rust.sh
scripts/ci/ci_install_rust.sh
+0
-0
No files found.
.github/workflows/execute-notebook.yml
View file @
2c7f01bc
...
...
@@ -24,7 +24,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
pip install -r docs/requirements.txt
apt-get update && apt-get install -y pandoc parallel retry
ln -sf "$(which python3)" /usr/bin/python
...
...
.github/workflows/experiment-runner.yml
View file @
2c7f01bc
...
...
@@ -21,7 +21,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Test experiment runner
timeout-minutes
:
120
...
...
.github/workflows/nightly-test-amd.yml
View file @
2c7f01bc
...
...
@@ -28,14 +28,14 @@ jobs:
-
name
:
Setup docker
run
:
|
touch github_summary.md
bash scripts/amd_ci_start_container.sh
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
bash scripts/amd_ci_install_dependency.sh
run
:
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
Nightly Test
run
:
|
bash scripts/amd_ci_exec.sh -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" python3 run_suite.py --suite nightly-amd --timeout-per-file 7200
bash scripts/
ci/
amd_ci_exec.sh -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" python3 run_suite.py --suite nightly-amd --timeout-per-file 7200
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY
.github/workflows/nightly-test.yml
View file @
2c7f01bc
...
...
@@ -24,7 +24,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
120
...
...
.github/workflows/pr-benchmark-rust.yml
View file @
2c7f01bc
...
...
@@ -31,7 +31,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_rust.sh
bash scripts/ci
/ci
_install_rust.sh
-
name
:
Cache Rust dependencies
uses
:
actions/cache@v4
...
...
@@ -78,7 +78,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_rust.sh
bash scripts/ci
/ci
_install_rust.sh
-
name
:
Cache Rust dependencies
uses
:
actions/cache@v4
...
...
.github/workflows/pr-test-amd.yml
View file @
2c7f01bc
...
...
@@ -36,19 +36,19 @@ jobs:
uses
:
actions/checkout@v4
-
name
:
Start CI container
run
:
bash scripts/amd_ci_start_container.sh
run
:
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
bash scripts/amd_ci_install_dependency.sh
run
:
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
Evaluate Accuracy
timeout-minutes
:
30
run
:
|
bash scripts/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
bash scripts/amd_ci_exec.sh python3 test_eval_fp8_accuracy.py
bash scripts/amd_ci_exec.sh python3 models/test_qwen_models.py
bash scripts/
ci/
amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
bash scripts/
ci/
amd_ci_exec.sh python3 test_eval_fp8_accuracy.py
bash scripts/
ci/
amd_ci_exec.sh python3 models/test_qwen_models.py
accuracy-test-2-gpu-amd
:
if
:
(github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
...
...
@@ -62,17 +62,17 @@ jobs:
uses
:
actions/checkout@v4
-
name
:
Start CI container
run
:
bash scripts/amd_ci_start_container.sh
run
:
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
bash scripts/amd_ci_install_dependency.sh
run
:
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
Evaluate accuracy (TP=2)
timeout-minutes
:
30
run
:
|
bash scripts/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_moe_eval_accuracy_large.py
bash scripts/
ci/
amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_moe_eval_accuracy_large.py
mla-test-1-gpu-amd
:
if
:
(github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
...
...
@@ -86,17 +86,17 @@ jobs:
uses
:
actions/checkout@v4
-
name
:
Start CI container
run
:
bash scripts/amd_ci_start_container.sh
run
:
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
bash scripts/amd_ci_install_dependency.sh
run
:
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
MLA TEST
timeout-minutes
:
30
run
:
|
bash scripts/amd_ci_exec.sh python3 test_mla.py
bash scripts/
ci/
amd_ci_exec.sh python3 test_mla.py
performance-test-1-gpu-part-1-amd
:
if
:
(github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
...
...
@@ -110,33 +110,33 @@ jobs:
uses
:
actions/checkout@v4
-
name
:
Start CI container
run
:
bash scripts/amd_ci_start_container.sh
run
:
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
bash scripts/amd_ci_install_dependency.sh
run
:
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
Benchmark single latency
timeout-minutes
:
20
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_small
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_default
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_small
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_default
-
name
:
Benchmark online latency
timeout-minutes
:
15
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default
-
name
:
Benchmark offline throughput
timeout-minutes
:
15
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default
-
name
:
Benchmark offline throughput (Non-streaming, small batch size)
timeout-minutes
:
15
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
performance-test-1-gpu-part-2-amd
:
if
:
(github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
...
...
@@ -150,27 +150,27 @@ jobs:
uses
:
actions/checkout@v4
-
name
:
Start CI container
run
:
bash scripts/amd_ci_start_container.sh
run
:
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
bash scripts/amd_ci_install_dependency.sh
run
:
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
Benchmark offline throughput (w/o RadixAttention)
timeout-minutes
:
15
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_without_radix_cache
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_without_radix_cache
-
name
:
Benchmark offline throughput (w/ Triton)
timeout-minutes
:
15
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend
-
name
:
Benchmark offline throughput (w/ FP8)
timeout-minutes
:
15
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
bench-test-2-gpu-amd
:
if
:
(github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
...
...
@@ -184,37 +184,37 @@ jobs:
uses
:
actions/checkout@v4
-
name
:
Start CI container
run
:
bash scripts/amd_ci_start_container.sh
run
:
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
bash scripts/amd_ci_install_dependency.sh
run
:
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
Benchmark dummy grok (TP=2)
timeout-minutes
:
30
run
:
|
bash scripts/amd_ci_exec.sh python3 models/test_dummy_grok_models.py
bash scripts/
ci/
amd_ci_exec.sh python3 models/test_dummy_grok_models.py
-
name
:
Benchmark single latency (TP=2)
timeout-minutes
:
25
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
-
name
:
Benchmark single latency + torch.compile (TP=2)
timeout-minutes
:
25
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_torch_compile_tp2_bs1
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_torch_compile_tp2_bs1
-
name
:
Benchmark offline throughput (TP=2)
timeout-minutes
:
25
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_default
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_default
-
name
:
Benchmark offline throughput (w/o RadixAttention) (TP=2)
timeout-minutes
:
25
run
:
|
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
bash scripts/
ci/
amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
unit-test-backend-1-gpu-amd
:
if
:
(github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
...
...
@@ -230,17 +230,17 @@ jobs:
uses
:
actions/checkout@v4
-
name
:
Start CI container
run
:
bash scripts/amd_ci_start_container.sh
run
:
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
bash scripts/amd_ci_install_dependency.sh
run
:
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
50
run
:
|
bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 7
bash scripts/
ci/
amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 7
unit-test-backend-2-gpu-amd
:
if
:
(github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
...
...
@@ -254,17 +254,17 @@ jobs:
uses
:
actions/checkout@v4
-
name
:
Start CI container
run
:
bash scripts/amd_ci_start_container.sh
run
:
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
bash scripts/amd_ci_install_dependency.sh
run
:
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
40
run
:
|
bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-2-gpu-amd
bash scripts/
ci/
amd_ci_exec.sh python3 run_suite.py --suite per-commit-2-gpu-amd
unit-test-backend-8-gpu-amd
:
if
:
(github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
...
...
@@ -278,22 +278,22 @@ jobs:
uses
:
actions/checkout@v4
-
name
:
Start CI container
run
:
bash scripts/amd_ci_start_container.sh
run
:
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
bash scripts/amd_ci_install_dependency.sh
run
:
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
60
run
:
|
bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-8-gpu-amd --timeout-per-file 3600
bash scripts/
ci/
amd_ci_exec.sh python3 run_suite.py --suite per-commit-8-gpu-amd --timeout-per-file 3600
-
name
:
Run CustomAllReduce test
timeout-minutes
:
20
run
:
|
bash scripts/amd_ci_exec.sh -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 -m unittest test_custom_allreduce.TestCustomAllReduce
bash scripts/
ci/
amd_ci_exec.sh -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 -m unittest test_custom_allreduce.TestCustomAllReduce
unit-test-sgl-kernel-amd
:
if
:
(github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
...
...
@@ -308,13 +308,13 @@ jobs:
uses
:
actions/checkout@v4
-
name
:
Start CI container
run
:
bash scripts/amd_ci_start_container.sh
run
:
bash scripts/
ci/
amd_ci_start_container.sh
env
:
GITHUB_WORKSPACE
:
${{ github.workspace }}
-
name
:
Install dependencies
run
:
|
bash scripts/amd_ci_install_dependency.sh
bash scripts/
ci/
amd_ci_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
10
...
...
.github/workflows/pr-test-npu.yml
View file @
2c7f01bc
...
...
@@ -34,7 +34,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/npu_ci_install_dependency.sh
bash scripts/
ci/
npu_ci_install_dependency.sh
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
...
...
@@ -63,7 +63,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/npu_ci_install_dependency.sh
bash scripts/
ci/
npu_ci_install_dependency.sh
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
...
...
@@ -92,7 +92,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/npu_ci_install_dependency.sh
bash scripts/
ci/
npu_ci_install_dependency.sh
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
...
...
.github/workflows/pr-test-pd-router.yml
View file @
2c7f01bc
...
...
@@ -5,13 +5,13 @@ on:
branches
:
[
main
]
paths
:
-
'
python/sglang/srt/disaggregation/**'
-
'
scripts/ci_start_disaggregation_servers.sh'
-
'
scripts/ci
/ci
_start_disaggregation_servers.sh'
-
'
sgl-router/**'
pull_request
:
branches
:
[
main
]
paths
:
-
'
python/sglang/srt/disaggregation/**'
-
'
scripts/ci_start_disaggregation_servers.sh'
-
'
scripts/ci
/ci
_start_disaggregation_servers.sh'
-
'
sgl-router/**'
workflow_dispatch
:
...
...
@@ -44,7 +44,7 @@ jobs:
-
name
:
Setup Rust
run
:
|
bash scripts/ci_install_rust.sh
bash scripts/ci
/ci
_install_rust.sh
-
name
:
Cache Rust dependencies
uses
:
actions/cache@v4
...
...
@@ -132,7 +132,7 @@ jobs:
id
:
start_servers
run
:
|
echo "Starting disaggregation servers..."
bash scripts/ci_start_disaggregation_servers.sh &
bash scripts/ci
/ci
_start_disaggregation_servers.sh &
SERVER_PID=$!
echo "server_pid=$SERVER_PID" >> $GITHUB_OUTPUT
...
...
.github/workflows/pr-test-rust.yml
View file @
2c7f01bc
...
...
@@ -25,7 +25,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_rust.sh
bash scripts/ci
/ci
_install_rust.sh
-
name
:
Run fmt
run
:
|
...
...
@@ -64,7 +64,7 @@ jobs:
-
name
:
Install rust dependencies
run
:
|
bash scripts/ci_install_rust.sh
bash scripts/ci
/ci
_install_rust.sh
-
name
:
Build python binding
run
:
|
...
...
.github/workflows/pr-test-sgl-kernel.yml
View file @
2c7f01bc
...
...
@@ -84,7 +84,7 @@ jobs:
-
name
:
Install
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu126 && pip3 install pytest
pip3 uninstall sgl-kernel -y || true
pip3 install sgl-kernel/dist/*whl --force-reinstall --no-deps
...
...
@@ -116,7 +116,7 @@ jobs:
-
name
:
Install
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu126
pip3 uninstall sgl-kernel -y || true
pip3 install sgl-kernel/dist/*whl --force-reinstall --no-deps
...
...
.github/workflows/pr-test.yml
View file @
2c7f01bc
...
...
@@ -52,7 +52,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
10
...
...
@@ -76,7 +76,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
30
...
...
@@ -96,7 +96,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
30
...
...
@@ -120,7 +120,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
20
...
...
@@ -144,7 +144,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
20
...
...
@@ -164,7 +164,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Benchmark single latency
timeout-minutes
:
10
...
...
@@ -216,7 +216,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Benchmark offline throughput (w/o RadixAttention)
timeout-minutes
:
10
...
...
@@ -260,7 +260,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Benchmark single latency (TP=2)
timeout-minutes
:
10
...
...
@@ -310,7 +310,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
git clone https://github.com/merrymercy/human-eval.git
cd human-eval
pip install -e .
...
...
@@ -333,7 +333,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
git clone https://github.com/merrymercy/human-eval.git
cd human-eval
pip install -e .
...
...
@@ -356,7 +356,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_deepep.sh
bash scripts/ci
/ci
_install_deepep.sh
-
name
:
Run test
timeout-minutes
:
20
...
...
@@ -376,7 +376,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_deepep.sh
bash scripts/ci
/ci
_install_deepep.sh
-
name
:
Run test
timeout-minutes
:
20
...
...
@@ -398,7 +398,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
IS_BLACKWELL=1 bash scripts/ci_install_dependency.sh
IS_BLACKWELL=1 bash scripts/ci
/ci
_install_dependency.sh
-
name
:
Run test
timeout-minutes
:
20
...
...
.github/workflows/release-docs.yml
View file @
2c7f01bc
...
...
@@ -24,29 +24,28 @@ jobs:
-
name
:
Install dependencies
run
:
|
find /public_sglang_ci/runner-a-gpu-1/_work/_tool/Python/3.10.13/x64/lib/python3.10/site-packages -name "sgl-kernel*" -exec rm -rf {} + || true
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
pip install -r docs/requirements.txt
apt-get update
apt-get install -y pandoc
apt-get update && apt-get install -y parallel retry
apt-get update && apt-get install -y pandoc parallel retry
ln -sf "$(which python3)" /usr/bin/python
-
name
:
Setup Jupyter Kernel
run
:
|
python -m ipykernel install --user --name python3 --display-name "Python 3"
-
name
:
Execute notebooks and push to documents
env
:
GITHUB_TOKEN
:
${{ secrets.DOCUMENTATION_PAT_TOKEN }}
-
name
:
Execute notebooks
timeout-minutes
:
40
run
:
|
cd docs
make clean
make compile
-
name
:
Push HTML to sgl-project.github.io
run
:
|
cd docs
make html
python3 wrap_run_llm.py
cd _build/html
git clone https://$GITHUB_TOKEN@github.com/sgl-project/sgl-project.github.io.git ../sgl-project.github.io --depth 1
...
...
.github/workflows/vllm-dependency-test.yml
View file @
2c7f01bc
...
...
@@ -29,7 +29,7 @@ jobs:
-
name
:
Install dependencies
run
:
|
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
pip install "vllm==0.10.0"
pip install "openai==1.99.1"
pip install "bitsandbytes>=0.44.0"
...
...
README.md
View file @
2c7f01bc
...
...
@@ -16,7 +16,7 @@
|
[
**Documentation**
](
https://docs.sglang.ai/
)
|
[
**Join Slack**
](
https://slack.sglang.ai/
)
|
[
**Join Bi-Weekly Development Meeting**
](
https://meeting.sglang.ai/
)
|
[
**Roadmap**
](
https://github.com/sgl-project/sglang/issues/
4042
)
|
[
**Roadmap**
](
https://github.com/sgl-project/sglang/issues/
7736
)
|
[
**Slides**
](
https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#slides
)
|
## News
...
...
scripts/amd_ci_exec.sh
→
scripts/
ci/
amd_ci_exec.sh
View file @
2c7f01bc
File moved
scripts/amd_ci_install_dependency.sh
→
scripts/
ci/
amd_ci_install_dependency.sh
View file @
2c7f01bc
File moved
scripts/amd_ci_start_container.sh
→
scripts/
ci/
amd_ci_start_container.sh
View file @
2c7f01bc
...
...
@@ -3,7 +3,7 @@ set -euo pipefail
# Get version from SGLang version.py file
FALLBACK_SGLANG_VERSION
=
"v0.4.10.post2"
SGLANG_VERSION_FILE
=
"
$(
dirname
"
$0
"
)
/../python/sglang/version.py"
SGLANG_VERSION_FILE
=
"
$(
dirname
"
$0
"
)
/../
../
python/sglang/version.py"
if
[
-f
"
$SGLANG_VERSION_FILE
"
]
;
then
SGLANG_VERSION
=
$(
python3
-c
'
...
...
scripts/ci_install_deepep.sh
→
scripts/ci
/ci
_install_deepep.sh
View file @
2c7f01bc
...
...
@@ -2,7 +2,7 @@
# Install the dependency in CI.
set
-euxo
pipefail
bash scripts/ci_install_dependency.sh
bash scripts/ci
/ci
_install_dependency.sh
export
GDRCOPY_HOME
=
/usr/src/gdrdrv-2.4.4/
export
NVSHMEM_DIR
=
/opt/nvshmem/install
...
...
scripts/ci_install_dependency.sh
→
scripts/ci
/ci
_install_dependency.sh
View file @
2c7f01bc
...
...
@@ -12,7 +12,7 @@ fi
# Kill existing processes
SCRIPT_DIR
=
"
$(
cd
"
$(
dirname
"
${
BASH_SOURCE
[0]
}
"
)
"
&&
pwd
)
"
bash
"
${
SCRIPT_DIR
}
/killall_sglang.sh"
bash
"
${
SCRIPT_DIR
}
/
../
killall_sglang.sh"
# Install apt packages
apt
install
-y
git libnuma-dev
...
...
scripts/ci_install_rust.sh
→
scripts/ci
/ci
_install_rust.sh
View file @
2c7f01bc
File moved
Prev
1
2
3
4
Next
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment