Merge tag 'v0.6.0' into v0.6.0-dev

format.sh

@@ -99,7 +99,6 @@ echo 'vLLM mypy:'
 mypy --follow-imports skip  # Note that this is less strict than CI
 mypy tests --follow-imports skip
 mypy vllm/attention --follow-imports skip
-mypy vllm/core --follow-imports skip
 mypy vllm/distributed --follow-imports skip
 mypy vllm/engine  --follow-imports skip
 mypy vllm/executor --follow-imports skip

pyproject.toml

@@ -58,6 +58,7 @@ files = [
     "vllm/adapter_commons",
     "vllm/assets",
     "vllm/entrypoints",
+    "vllm/core",
     "vllm/inputs",
     "vllm/logging",
     "vllm/multimodal",

requirements-common.txt

@@ -20,9 +20,10 @@ lm-format-enforcer == 0.10.6
 outlines >= 0.0.43, < 0.1 # Requires torch >= 2.1.0
 typing_extensions >= 4.10
 filelock >= 3.10.4 # filelock starts to support `mode` argument from 3.10.4
+partial-json-parser # used for parsing partial JSON outputs
 pyzmq
 msgspec
-librosa # Required for audio processing
-soundfile # Required for audio processing
 gguf == 0.9.1
 importlib_metadata
+mistral_common >= 1.3.4
+pyyaml

requirements-mamba.txt

-# Mamba dependencies
-mamba-ssm>=1.2.2
-causal-conv1d>=1.2.0

requirements-rocm.txt

@@ -8,3 +8,4 @@ botocore
 ray >= 2.10.0
 peft
 pytest-asyncio
+tensorizer>=2.9.0
\ No newline at end of file

requirements-tpu.txt

@@ -4,4 +4,4 @@
 # Dependencies for TPU
 # Currently, the TPU backend uses a nightly version of PyTorch XLA.
 # You can install the dependencies in Dockerfile.tpu.
-ray
+ray[default]