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

Update install commands (#583)

Browse Source
This commit is contained in:
Lianmin Zheng
2024-07-03 02:07:34 -07:00
parent 9380f50ff9
commit c7709d3abe
3 changed files with 17 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python/pyproject.toml
View File

@@ -20,8 +20,8 @@ dependencies = [
]
[project.optional-dependencies]
srt = ["aiohttp", "fastapi", "psutil", "rpyc", "torch", "uvloop", "uvicorn",
"zmq", "vllm==0.5.0", "interegular", "pydantic", "pillow", "packaging", "huggingface_hub", "hf_transfer", "outlines>=0.0.44"]
srt = ["aiohttp", "fastapi", "hf_transfer", "huggingface_hub", "interegular", "packaging", "pillow",
"psutil", "pydantic", "rpyc", "torch", "uvicorn", "uvloop", "zmq", "vllm==0.5.0", "outlines>=0.0.44"]
openai = ["openai>=1.0", "tiktoken"]
anthropic = ["anthropic>=0.20.0"]
litellm = ["litellm>=1.0.0"]

11
python/sglang/srt/server_args.py
View File

@@ -291,11 +291,6 @@ class ServerArgs:
action="store_true",
help="Disable flashinfer inference kernels",
)
parser.add_argument(
"--attention-reduce-in-fp32",
action="store_true",
help="Cast the intermidiate attention results to fp32 to avoid possible crashes related to fp16.",
)
parser.add_argument(
"--disable-radix-cache",
action="store_true",
@@ -311,6 +306,12 @@ class ServerArgs:
action="store_true",
help="Disable disk cache to avoid possible crashes related to file system or high concurrency.",
)
parser.add_argument(
"--attention-reduce-in-fp32",
action="store_true",
help="Cast the intermidiate attention results to fp32 to avoid possible crashes related to fp16."
"This only affects Triton attention kernels",
)
@classmethod
def from_cli_args(cls, args: argparse.Namespace):