Release v0.3.5.post1 (#2022)

Author: merrymercy

docker/Dockerfile.rocm

@@ -1,5 +1,5 @@
 # Usage (to build SGLang ROCm docker image):
-#   docker build --build-arg SGL_BRANCH=v0.3.5 -t testImage -f Dockerfile.rocm .
+#   docker build --build-arg SGL_BRANCH=v0.3.5.post1 -t testImage -f Dockerfile.rocm .
 
 # default base image
 ARG BASE_IMAGE="rocm/vllm-dev:20241022"

docs/start/install.md

@@ -16,7 +16,7 @@ Note: Please check the [FlashInfer installation doc](https://docs.flashinfer.ai/
 ## Method 2: From source
 ```
 # Use the last release branch
-git clone -b v0.3.5 https://github.com/sgl-project/sglang.git
+git clone -b v0.3.5.post1 https://github.com/sgl-project/sglang.git
 cd sglang
 
 pip install --upgrade pip
@@ -46,7 +46,7 @@ docker run --gpus all \
 Note: To AMD ROCm system with Instinct/MI GPUs, it is recommended to use `docker/Dockerfile.rocm` to build images, example and usage as below:
 
 ```bash
-docker build --build-arg SGL_BRANCH=v0.3.5 -t v0.3.5-rocm620 -f Dockerfile.rocm .
+docker build --build-arg SGL_BRANCH=v0.3.5.post1 -t v0.3.5.post1-rocm620 -f Dockerfile.rocm .
 
 alias drun='docker run -it --rm --network=host --device=/dev/kfd --device=/dev/dri --ipc=host \
     --shm-size 16G --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \
@@ -55,11 +55,11 @@ alias drun='docker run -it --rm --network=host --device=/dev/kfd --device=/dev/d
 drun -p 30000:30000 \
     -v ~/.cache/huggingface:/root/.cache/huggingface \
     --env "HF_TOKEN=<secret>" \
-    v0.3.5-rocm620 \
+    v0.3.5.post1-rocm620 \
     python3 -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --host 0.0.0.0 --port 30000
 
 # Till flashinfer backend available, --attention-backend triton --sampling-backend pytorch are set by default
-drun v0.3.5-rocm620 python3 -m sglang.bench_latency --batch-size 32 --input 1024 --output 128 --model amd/Meta-Llama-3.1-8B-Instruct-FP8-KV --tp 8 --quantization fp8
+drun v0.3.5.post1-rocm620 python3 -m sglang.bench_latency --batch-size 32 --input 1024 --output 128 --model amd/Meta-Llama-3.1-8B-Instruct-FP8-KV --tp 8 --quantization fp8
 ```
 
 ## Method 4: Using docker compose

python/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sglang"
-version = "0.3.5"
+version = "0.3.5.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__ = "0.3.5"
+__version__ = "0.3.5.post1"

test/srt/test_pytorch_sampling_backend.py

@@ -40,7 +40,7 @@ def test_mmlu(self):
         )
 
         metrics = run_eval(args)
-        assert metrics["score"] >= 0.65
+        self.assertGreaterEqual(metrics["score"], 0.65)
 
     def test_greedy(self):
 
@@ -62,7 +62,7 @@ def test_greedy(self):
             if first_text is None:
                 first_text = text
 
-            assert text == first_text, f'"{text}" is not identical to "{first_text}"'
+            self.assertEqual(text, first_text)
 
         first_text = None
 
@@ -82,7 +82,7 @@ def test_greedy(self):
             text = response_batch[i]["text"]
             if first_text is None:
                 first_text = text
-            assert text == first_text, f'"{text}" is not identical to "{first_text}"'
+            self.assertEqual(text, first_text)
 
 
 if __name__ == "__main__":