Dan Clark c17ca8ef18 Add args for mTLS support (#3410) ...

Co-authored-by: Daniel Clark <daniel.clark@ibm.com>

2024-03-14 13:11:45 -07:00

..

core

Fixes #1556 double free (#3347)

2024-03-13 00:30:08 +00:00

engine

Add distributed model executor abstraction (#3191)

2024-03-11 11:03:45 -07:00

entrypoints

Add args for mTLS support (#3410)

2024-03-14 13:11:45 -07:00

executor

[FIX] Simpler fix for async engine running on ray (#3371)

2024-03-13 14:18:40 -07:00

lora

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

model_executor

[Kernel] change benchmark script so that result can be directly used; tune moe kernel in A100/H100 with tp=2,4,8 (#3389)

2024-03-14 08:11:48 +00:00

spec_decode

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

transformers_utils

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

worker

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

__init__.py

Add distributed model executor abstraction (#3191)

2024-03-11 11:03:45 -07:00

block.py

Add Automatic Prefix Caching (#2762)

2024-03-02 00:50:01 -08:00

config.py

[Fix] Fix quantization="gptq" when using Marlin (#3319)

2024-03-12 22:51:42 -07:00

logger.py

Make vLLM logging formatting optional (#2877)

2024-02-20 14:38:55 -08:00

outputs.py

[Fix] Fix best_of behavior when n=1 (#3298)

2024-03-10 19:17:46 -07:00

py.typed

Add py.typed so consumers of vLLM can get type checking (#1509)

2023-10-30 14:50:47 -07:00

sampling_params.py

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

sequence.py

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

test_utils.py

Use CuPy for CUDA graphs (#2811)

2024-02-13 11:32:06 -08:00

utils.py

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00