leiwen83andLei Wen b38e42fbca [Speculative decoding] Add ngram prompt lookup decoding (#4237) ...

Co-authored-by: Lei Wen <wenlei03@qiyi.com>

2024-05-01 11:13:03 -07:00

..

async_engine

[Bugfix] Abort requests when the connection to /v1/completions is interrupted (#4363)

2024-04-27 09:48:37 -07:00

basic_correctness

…

core

[Core] Scheduling optimization 2 (#4280)

2024-04-23 08:02:11 +00:00

distributed

[Core][Distributed] use cpu/gloo to initialize pynccl (#4248)

2024-04-23 18:32:19 -07:00

engine

Make initialization of tokenizer and detokenizer optional (#3748)

2024-04-21 22:06:46 +00:00

entrypoints

Allow user to define whitespace pattern for outlines (#4305)

2024-04-30 20:48:39 -07:00

fp8_kv

…

kernels

[Bugfix][Kernel] allow non-power-of-two head sizes in prefix prefill (#4128)

2024-04-18 00:51:28 -07:00

lora

[Kernel] Full Tensor Parallelism for LoRA Layers (#3524)

2024-04-27 00:03:48 -07:00

metrics

…

model_executor

[Core] Support offline use of local cache for models (#4374)

2024-04-27 09:59:55 -07:00

models

[Misc]Add customized information for models (#4132)

2024-04-30 21:18:14 -07:00

prefix_caching

…

prompts

…

quantization

[Kernel] Marlin Expansion: Support AutoGPTQ Models with Marlin (#3922)

2024-04-29 09:35:34 -07:00

samplers

[Test] Add ignore_eos test (#4519)

2024-05-01 08:45:42 -04:00

spec_decode

[Speculative decoding] Add ngram prompt lookup decoding (#4237)

2024-05-01 11:13:03 -07:00

tensorizer_loader

[Core][Distributed] use cpu group to broadcast metadata in cpu (#4444)

2024-04-29 13:52:22 -07:00

tokenization

[Bugfix] Fix parameter name in get_tokenizer (#4107)

2024-04-25 19:10:48 -07:00

worker

[Core][Distributed] use cpu group to broadcast metadata in cpu (#4444)

2024-04-29 13:52:22 -07:00

__init__.py

…

conftest.py

…

test_cache_block_hashing.py

…

test_config.py

…

test_logger.py

[Core] add an option to log every function call to for debugging hang/crash in distributed inference (#4079)

2024-04-18 16:15:12 -07:00

test_logits_processor.py

[Core] Refactoring sampler and support prompt logprob for chunked prefill (#4309)

2024-04-26 13:02:02 +00:00

test_regression.py

…

test_sampling_params.py

…

test_sequence.py

…