From 59e8ef93dce2f0caa7b5c9bf9cd5f97a4f7ddbdf Mon Sep 17 00:00:00 2001
From: Aaron <29749331+aarnphm@users.noreply.github.com>
Date: Tue, 12 Dec 2023 00:17:18 -0500
Subject: [PATCH] chore(deps): lock vLLM to 0.2.4

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
---
 openllm-python/pyproject.toml                 | 6 +++---
 openllm-python/src/openllm/bundle/_package.py | 8 ++++----
 tools/dependencies.py                         | 4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/openllm-python/pyproject.toml b/openllm-python/pyproject.toml
index b329c6a2..6d89f7ba 100644
--- a/openllm-python/pyproject.toml
+++ b/openllm-python/pyproject.toml
@@ -39,7 +39,7 @@ classifiers = [
 ]
 dependencies = [
     "bentoml[io]>=1.1.10",
-    "transformers[torch,tokenizers]>=4.35.0",
+    "transformers[torch,tokenizers]>=4.36.0",
     "openllm-client>=0.4.35",
     "openllm-core>=0.4.35",
     "safetensors",
@@ -100,7 +100,7 @@ Tracker = "https://github.com/bentoml/OpenLLM/issues"
 Twitter = "https://twitter.com/bentomlai"
 
 [project.optional-dependencies]
-agents = ["transformers[agents]>=4.35.0", "diffusers", "soundfile"]
+agents = ["transformers[agents]>=4.36.0", "diffusers", "soundfile"]
 all = ["openllm[full]"]
 awq = ["autoawq"]
 baichuan = ["cpm-kernels"]
@@ -119,7 +119,7 @@ openai = ["openai[datalib]>=1", "tiktoken"]
 playground = ["jupyter", "notebook", "ipython", "jupytext", "nbformat"]
 qwen = ["cpm-kernels", "tiktoken"]
 starcoder = ["bitsandbytes"]
-vllm = ["vllm>=0.2.2"]
+vllm = ["vllm>=0.2.4"]
 
 [tool.hatch.version]
 fallback-version = "0.0.0"
diff --git a/openllm-python/src/openllm/bundle/_package.py b/openllm-python/src/openllm/bundle/_package.py
index b3ed98db..e83f0a53 100644
--- a/openllm-python/src/openllm/bundle/_package.py
+++ b/openllm-python/src/openllm/bundle/_package.py
@@ -31,7 +31,7 @@ def build_editable(path, package='openllm'):
   raise RuntimeError('Please install OpenLLM from PyPI or built it from Git source.')
 def construct_python_options(llm, llm_fs, extra_dependencies=None, adapter_map=None):
   from . import RefResolver
-  packages = ['scipy', 'bentoml[tracing]>=1.1.10', 'vllm==0.2.2', 'ray==2.6.0', f'openllm>={RefResolver.from_strategy("release").version}']  # apparently bnb misses this one
+  packages = ['scipy', 'bentoml[tracing]>=1.1.10', 'vllm==0.2.4', 'ray==2.6.0', f'openllm>={RefResolver.from_strategy("release").version}']  # apparently bnb misses this one
   if adapter_map is not None: packages += ['openllm[fine-tune]']
   if extra_dependencies is not None: packages += [f'openllm[{k}]' for k in extra_dependencies]
   if llm.config['requirements'] is not None: packages.extend(llm.config['requirements'])
@@ -53,9 +53,9 @@ def construct_docker_options(llm, _, quantize, adapter_map, dockerfile_template,
   return DockerOptions(cuda_version='12.1', env=environ, dockerfile_template=dockerfile_template)
 @inject
 def create_bento(
-  bento_tag, llm_fs, llm,
-  quantize, dockerfile_template,
-  adapter_map=None, extra_dependencies=None, serialisation=None,
+  bento_tag, llm_fs, llm, #
+  quantize, dockerfile_template, #
+  adapter_map=None, extra_dependencies=None, serialisation=None, #
   _bento_store=Provide[BentoMLContainer.bento_store], _model_store=Provide[BentoMLContainer.model_store],
 ):
   _serialisation = openllm_core.utils.first_not_none(serialisation, default=llm.config['serialisation'])
diff --git a/tools/dependencies.py b/tools/dependencies.py
index 1c44f8dc..74e640bd 100755
--- a/tools/dependencies.py
+++ b/tools/dependencies.py
@@ -144,7 +144,7 @@ class Dependencies:
 _LOWER_BENTOML_CONSTRAINT = '1.1.10'
 _BENTOML_EXT = ['io']
 _TRANSFORMERS_EXT = ['torch', 'tokenizers']
-_TRANSFORMERS_CONSTRAINTS = '4.35.0'
+_TRANSFORMERS_CONSTRAINTS = '4.36.0'
 
 FINE_TUNE_DEPS = ['peft>=0.6.0', 'datasets', 'trl', 'huggingface-hub']
 GRPC_DEPS = [f'bentoml[grpc]>={_LOWER_BENTOML_CONSTRAINT}']
@@ -155,7 +155,7 @@ GGML_DEPS = ['ctransformers']
 CTRANSLATE_DEPS = ['ctranslate2>=3.22.0']
 AWQ_DEPS = ['autoawq']
 GPTQ_DEPS = ['auto-gptq[triton]>=0.4.2']
-VLLM_DEPS = ['vllm>=0.2.2']
+VLLM_DEPS = ['vllm>=0.2.4']
 
 _base_requirements: dict[str, t.Any] = {
   inflection.dasherize(name): config_cls.__openllm_requirements__