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

Fix dependency (#538)

Browse Source
This commit is contained in:
Lianmin Zheng
2024-06-12 13:17:35 -07:00
committed by GitHub
parent 9c902b1954
commit 94aead9e8d
3 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/pyproject.toml
View File

@@ -21,7 +21,7 @@ dependencies = [
[project.optional-dependencies] [project.optional-dependencies]
srt = ["aiohttp", "fastapi", "psutil", "rpyc", "torch", "uvloop", "uvicorn", srt = ["aiohttp", "fastapi", "psutil", "rpyc", "torch", "uvloop", "uvicorn",
"zmq", "vllm==0.4.3", "interegular", "pydantic", "pillow", "packaging", "huggingface_hub", "hf_transfer", "outlines>=0.0.34"] "zmq", "vllm==0.4.3", "interegular", "pydantic", "pillow", "packaging", "huggingface_hub", "hf_transfer", "outlines>=0.0.41"]
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"]

2
python/sglang/srt/constrained/jump_forward.py
View File

@@ -3,10 +3,10 @@ Faster constrained decoding.
Reference: https://lmsys.org/blog/2024-02-05-compressed-fsm/ Reference: https://lmsys.org/blog/2024-02-05-compressed-fsm/
""" """
import interegular
import dataclasses import dataclasses
from collections import defaultdict from collections import defaultdict
import interegular
import outlines.caching import outlines.caching
from sglang.srt.constrained import ( from sglang.srt.constrained import (
FSMInfo, FSMInfo,

3
python/sglang/srt/models/chatglm.py
View File

@@ -5,7 +5,6 @@
from typing import Iterable, List, Optional, Tuple from typing import Iterable, List, Optional, Tuple
import torch import torch
from peft import LoraConfig
from sglang.srt.layers.radix_attention import RadixAttention from sglang.srt.layers.radix_attention import RadixAttention
from sglang.srt.managers.controller.model_runner import InputMetadata from sglang.srt.managers.controller.model_runner import InputMetadata
from sglang.srt.layers.logits_processor import LogitsProcessor from sglang.srt.layers.logits_processor import LogitsProcessor
@@ -31,6 +30,8 @@ from vllm.sequence import SamplerOutput
from vllm.transformers_utils.configs import ChatGLMConfig from vllm.transformers_utils.configs import ChatGLMConfig
LoraConfig = None
class GLMAttention(nn.Module): class GLMAttention(nn.Module):