Jinzhen Lin 33e0823de5

[Bugfix] fix rope error when load models with different dtypes (#4835)

2024-05-17 18:43:34 +09:00

..

async_engine

…

basic_correctness

…

core

…

distributed

[Core][Distributed] remove graph mode function (#4818)

2024-05-16 10:59:52 -07:00

engine

[Build/CI] Extending the set of AMD tests with Regression, Basic Correctness, Distributed, Engine, Llava Tests (#4797)

2024-05-16 20:58:25 -07:00

entrypoints

[Frontend] Support OpenAI batch file format (#4794)

2024-05-15 19:13:36 -04:00

fp8_kv

…

kernels

[Bugfix] fix rope error when load models with different dtypes (#4835)

2024-05-17 18:43:34 +09:00

lora

[Kernel] Add punica dimension for Qwen1.5-32B LoRA (#4850)

2024-05-16 11:16:09 -07:00

metrics

…

model_executor

…

models

Add GPTQ Marlin 2:4 sparse structured support (#4790)

2024-05-16 12:56:15 -04:00

prefix_caching

…

prompts

…

quantization

…

samplers

…

spec_decode

[Speculative decoding][Re-take] Enable TP>1 speculative decoding (#4840)

2024-05-16 00:53:51 -07:00

tensorizer_loader

…

tokenization

…

worker

…

__init__.py

…

conftest.py

…

test_cache_block_hashing.py

…

test_config.py

…

test_logger.py

…

test_logits_processor.py

…

test_regression.py

…

test_sampling_params.py

…

test_sequence.py

…

test_sharded_state_loader.py

[Core] Implement sharded state loader (#4690)

2024-05-15 22:11:54 -07:00

utils.py

…