| .. |
|
attention
|
[Misc]Add customized information for models (#4132)
|
2024-04-30 21:18:14 -07:00 |
|
core
|
[Core] Enable prefix caching with block manager v2 enabled (#4142)
|
2024-05-01 11:20:32 -07:00 |
|
distributed
|
[Core][Distributed] fix pynccl del error (#4508)
|
2024-05-01 15:23:06 -07:00 |
|
engine
|
[Bugfix][Core] Fix and refactor logging stats (#4336)
|
2024-05-01 20:08:14 +00:00 |
|
entrypoints
|
[Bugfix] Add validation for seed (#4529)
|
2024-05-01 19:31:22 +00:00 |
|
executor
|
[Core] Add multiproc_worker_utils for multiprocessing-based workers (#4357)
|
2024-05-01 18:41:59 +00:00 |
|
lora
|
[Kernel] Full Tensor Parallelism for LoRA Layers (#3524)
|
2024-04-27 00:03:48 -07:00 |
|
model_executor
|
[Misc] Remove Mixtral device="cuda" declarations (#4543)
|
2024-05-01 16:30:52 -07:00 |
|
spec_decode
|
[Speculative decoding] Add ngram prompt lookup decoding (#4237)
|
2024-05-01 11:13:03 -07:00 |
|
transformers_utils
|
fix_tokenizer_snapshot_download_bug (#4493)
|
2024-04-30 16:38:50 -07:00 |
|
usage
|
[mypy] Add mypy type annotation part 1 (#4006)
|
2024-04-12 14:35:50 -07:00 |
|
worker
|
[Core] Refactoring sampler and support prompt logprob for chunked prefill (#4309)
|
2024-04-26 13:02:02 +00:00 |
|
__init__.py
|
[Core] Move ray_utils.py from engine to executor package (#4347)
|
2024-04-25 06:52:22 +00:00 |
|
_custom_ops.py
|
[Core]Refactor gptq_marlin ops (#4466)
|
2024-04-30 08:14:47 -04:00 |
|
block.py
|
Add Automatic Prefix Caching (#2762)
|
2024-03-02 00:50:01 -08:00 |
|
config.py
|
[Speculative decoding] Add ngram prompt lookup decoding (#4237)
|
2024-05-01 11:13:03 -07:00 |
|
logger.py
|
[CI] Disable non-lazy string operation on logging (#4326)
|
2024-04-26 00:16:58 -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
|
[Bugfix] Use random seed if seed is -1 (#4531)
|
2024-05-01 10:41:17 -07:00 |
|
sequence.py
|
Add more Prometheus metrics (#2764)
|
2024-04-28 15:59:33 -07:00 |
|
test_utils.py
|
[Core][Refactor] move parallel_utils into vllm/distributed (#3950)
|
2024-04-10 15:33:30 -07:00 |
|
utils.py
|
[Bugfix] Abort requests when the connection to /v1/completions is interrupted (#4363)
|
2024-04-27 09:48:37 -07:00 |
