EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

chore: bump v0.2.14 (#1155)

Browse Source
This commit is contained in:
Yineng Zhang
2024-08-27 00:28:24 +10:00
committed by GitHub
parent 75ce37f401
commit c5fe11a8e1
4 changed files with 7 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -56,7 +56,7 @@ pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
### Method 2: From source ### Method 2: From source
``` ```
# Use the last release branch # Use the last release branch
git clone -b v0.2.13 https://github.com/sgl-project/sglang.git git clone -b v0.2.14 https://github.com/sgl-project/sglang.git
cd sglang cd sglang
pip install --upgrade pip pip install --upgrade pip

4
python/pyproject.toml
View File

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
[project] [project]
name = "sglang" name = "sglang"
version = "0.2.13" version = "0.2.14"
description = "SGLang is yet another fast serving framework for large language models and vision language models." description = "SGLang is yet another fast serving framework for large language models and vision language models."
readme = "README.md" readme = "README.md"
requires-python = ">=3.8" requires-python = ">=3.8"
@@ -23,7 +23,7 @@ dependencies = [
srt = ["aiohttp", "decord", "fastapi", "hf_transfer", "huggingface_hub", "interegular", srt = ["aiohttp", "decord", "fastapi", "hf_transfer", "huggingface_hub", "interegular",
"packaging", "pillow", "psutil", "pydantic", "python-multipart", "packaging", "pillow", "psutil", "pydantic", "python-multipart",
"torch", "uvicorn", "uvloop", "zmq", "torch", "uvicorn", "uvloop", "zmq",
"vllm==0.5.4", "outlines>=0.0.44"] "vllm==0.5.5", "outlines>=0.0.44"]
openai = ["openai>=1.0", "tiktoken"] openai = ["openai>=1.0", "tiktoken"]
anthropic = ["anthropic>=0.20.0"] anthropic = ["anthropic>=0.20.0"]
litellm = ["litellm>=1.0.0"] litellm = ["litellm>=1.0.0"]

7
python/sglang/srt/model_executor/model_runner.py
View File

@@ -191,12 +191,11 @@ class ModelRunner:
self.model = get_model( self.model = get_model(
model_config=self.vllm_model_config, model_config=self.vllm_model_config,
device_config=self.device_config,
load_config=self.load_config, load_config=self.load_config,
lora_config=None, device_config=self.device_config,
multimodal_config=None,
parallel_config=None, parallel_config=None,
scheduler_config=None, scheduler_config=None,
lora_config=None,
cache_config=None, cache_config=None,
) )
self.sliding_window_size = ( self.sliding_window_size = (
@@ -627,4 +626,4 @@ def load_model_cls_srt(model_arch: str) -> Optional[Type[nn.Module]]:
# Monkey patch model loader # Monkey patch model loader
setattr(ModelRegistry, "load_model_cls", load_model_cls_srt) setattr(ModelRegistry, "_try_load_model_cls", load_model_cls_srt)

2
python/sglang/version.py
View File

@@ -1 +1 @@
__version__ = "0.2.13" __version__ = "0.2.14"