Release v0.3.3.post1 (#1636)

.github/workflows/pr-test.yml

@@ -56,7 +56,7 @@ jobs:
         timeout-minutes: 20
         run: |
           cd test/srt
-          python3 run_suite.py --suite minimal --range-begin 0 --range-end 7
+          python3 run_suite.py --suite minimal --range-begin 0 --range-end 5
 
   unit-test-backend-part-2:
     if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
@@ -76,7 +76,7 @@ jobs:
         timeout-minutes: 20
         run: |
           cd test/srt
-          python3 run_suite.py --suite minimal --range-begin 7 --range-end 14
+          python3 run_suite.py --suite minimal --range-begin 5 --range-end 16
 
   unit-test-backend-part-3:
     if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
@@ -96,7 +96,7 @@ jobs:
         timeout-minutes: 20
         run: |
           cd test/srt
-          python3 run_suite.py --suite minimal --range-begin 14
+          python3 run_suite.py --suite minimal --range-begin 16
 
   performance-test-1-gpu-part-1:
     if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'

README.md

@@ -64,7 +64,7 @@ pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
 ### Method 2: From source
 ```
 # Use the last release branch
-git clone -b v0.3.3 https://github.com/sgl-project/sglang.git
+git clone -b v0.3.3.post1 https://github.com/sgl-project/sglang.git
 cd sglang
 
 pip install --upgrade pip

python/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sglang"
-version = "0.3.3"
+version = "0.3.3.post1"
 description = "SGLang is yet another fast serving framework for large language models and vision language models."
 readme = "README.md"
 requires-python = ">=3.8"

python/sglang/version.py

@@ -1 +1 @@
-__version__ = "0.3.3"
+__version__ = "0.3.3.post1"