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

Simplify frontend language (#9029)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-08-10 10:59:30 -07:00
committed by GitHub
parent 6345069f6c
commit b58ae7a2a0
9 changed files with 19 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
python/pyproject.toml
View File

@@ -47,10 +47,10 @@ runtime_common = [
"sentencepiece",
"soundfile==0.13.1",
"scipy",
"torchao==0.9.0",
"transformers==4.55.0",
"timm==1.0.16",
"tiktoken",
"torchao==0.9.0",
"transformers==4.55.0",
"uvicorn",
"uvloop",
"xgrammar==0.1.22",
@@ -84,6 +84,9 @@ srt_hip = [
"petit_kernel==0.0.2",
]
# CPU: torch wheel for CPU needs to be installed from https://download.pytorch.org/whl/cpu
srt_cpu = ["sglang[runtime_common]", "einops"]
# xpu is not enabled in public vllm and torch whl,
# need to follow https://docs.vllm.ai/en/latest/getting_started/xpu-installation.htmlinstall vllm
srt_xpu = ["sglang[runtime_common]"]
@@ -92,8 +95,6 @@ srt_xpu = ["sglang[runtime_common]"]
# https://docs.vllm.ai/en/latest/getting_started/gaudi-installation.html
srt_hpu = ["sglang[runtime_common]"]
# CPU: torch wheel for CPU needs to be installed from https://download.pytorch.org/whl/cpu
srt_cpu = ["sglang[runtime_common]", "einops"]
# https://vllm-ascend.readthedocs.io/en/latest/installation.html
srt_npu = ["sglang[runtime_common]"]
@@ -112,12 +113,12 @@ test = [
"sentence_transformers",
"pytest",
]
all = ["sglang[srt]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]", "sglang[torch_memory_saver]", "sglang[decord]"]
all_hip = ["sglang[srt_hip]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]", "sglang[decord]"]
all_xpu = ["sglang[srt_xpu]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]", "sglang[decord]"]
all_hpu = ["sglang[srt_hpu]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]", "sglang[decord]"]
all_cpu = ["sglang[srt_cpu]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]", "sglang[decord]"]
all_npu = ["sglang[srt_npu]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]", "sglang[decord]"]
all = ["sglang[srt]", "sglang[openai]", "sglang[anthropic]", "sglang[torch_memory_saver]", "sglang[decord]"]
all_hip = ["sglang[srt_hip]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
all_xpu = ["sglang[srt_xpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
all_hpu = ["sglang[srt_hpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
all_cpu = ["sglang[srt_cpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
all_npu = ["sglang[srt_npu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
dev = ["sglang[all]", "sglang[test]"]
dev_hip = ["sglang[all_hip]", "sglang[test]"]