| .. |
|
attention
|
Fix triton compilation issue (#3984)
|
2024-04-12 16:41:26 -07:00 |
|
core
|
[Speculative decoding 6/9] Integrate speculative decoding with LLMEngine (#3894)
|
2024-04-16 13:09:21 -07:00 |
|
distributed
|
[Core] avoid too many cuda context by caching p2p test (#4021)
|
2024-04-13 23:40:21 -07:00 |
|
engine
|
[Core] RayWorkerVllm --> WorkerWrapper to reduce duplication (#4024)
|
2024-04-17 08:34:33 +00:00 |
|
entrypoints
|
LM Format Enforcer Guided Decoding Support (#3868)
|
2024-04-16 05:54:57 +00:00 |
|
executor
|
[Core] RayWorkerVllm --> WorkerWrapper to reduce duplication (#4024)
|
2024-04-17 08:34:33 +00:00 |
|
lora
|
[Bugfix] Fix LoRA bug (#4032)
|
2024-04-12 16:56:37 -07:00 |
|
model_executor
|
[Core] Refactor model loading code (#4097)
|
2024-04-16 11:34:39 -07:00 |
|
spec_decode
|
[Speculative decoding 6/9] Integrate speculative decoding with LLMEngine (#3894)
|
2024-04-16 13:09:21 -07:00 |
|
transformers_utils
|
[Core] Refactor model loading code (#4097)
|
2024-04-16 11:34:39 -07:00 |
|
usage
|
[mypy] Add mypy type annotation part 1 (#4006)
|
2024-04-12 14:35:50 -07:00 |
|
worker
|
[Core] RayWorkerVllm --> WorkerWrapper to reduce duplication (#4024)
|
2024-04-17 08:34:33 +00:00 |
|
__init__.py
|
[Core] enable out-of-tree model register (#3871)
|
2024-04-06 17:11:41 -07:00 |
|
_custom_ops.py
|
[Misc] Add indirection layer for custom ops (#3913)
|
2024-04-10 20:26:07 -07:00 |
|
block.py
|
Add Automatic Prefix Caching (#2762)
|
2024-03-02 00:50:01 -08:00 |
|
config.py
|
[Core] Refactor model loading code (#4097)
|
2024-04-16 11:34:39 -07:00 |
|
logger.py
|
[Doc] Add typing hints / mypy types cleanup (#3816)
|
2024-04-11 17:17:21 -07:00 |
|
outputs.py
|
[BugFix] Fix handling of stop strings and stop token ids (#3672)
|
2024-04-11 15:34:12 -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
|
[mypy] Add mypy type annotation part 1 (#4006)
|
2024-04-12 14:35:50 -07:00 |
|
sequence.py
|
[Speculative decoding 6/9] Integrate speculative decoding with LLMEngine (#3894)
|
2024-04-16 13:09:21 -07:00 |
|
test_utils.py
|
[Core][Refactor] move parallel_utils into vllm/distributed (#3950)
|
2024-04-10 15:33:30 -07:00 |
|
utils.py
|
[Core] RayWorkerVllm --> WorkerWrapper to reduce duplication (#4024)
|
2024-04-17 08:34:33 +00:00 |
8438e0569e