vllm/vllm at main · lamini-ai/vllm · GitHub

8000 vllm/vllm at main · lamini-ai/vllm · GitHub

This repository was archived by the owner on Jun 13, 2025. It is now read-only.

Repository navigation

Name		Name	Last commit message	Last commit date
parent directory ..
adapter_commons		adapter_commons
assets		assets
attention		attention
compilation		compilation
core		core
distributed		distributed
engine		engine
entrypoints		entrypoints
executor		executor
inputs		inputs
logging_utils		logging_utils
lora		lora
model_executor		model_executor
multimodal		multimodal
platforms		platforms
plugins		plugins
profiler		profiler
prompt_adapter		prompt_adapter
spec_decode		spec_decode
transformers_utils		transformers_utils
triton_utils		triton_utils
usage		usage
v1		v1
vllm_flash_attn		vllm_flash_attn
worker		worker
__init__.py		__init__.py
_custom_ops.py		_custom_ops.py
_ipex_ops.py		_ipex_ops.py
beam_search.py		beam_search.py
config.py		config.py
connections.py		connections.py
envs.py		envs.py
forward_context.py		forward_context.py
logger.py		logger.py
logits_process.py		logits_process.py
outputs.py		outputs.py
pooling_params.py		pooling_params.py
py.typed		py.typed
sampling_params.py		sampling_params.py
scalar_type.py		scalar_type.py
scripts.py		scripts.py
sequence.py		sequence.py
tracing.py		tracing.py
utils.py		utils.py
version.py		version.py

0