3 people dacaf5a400 Replace head_mapping params with num_kv_heads to attention kernel. (#1997) ...

Co-authored-by: wangguoya <wangguoya@baidu.com>
Co-authored-by: Yang Zhao <zhaoyangstar@foxmail.com>

2023-12-10 10:12:53 -08:00

..

layers

Replace head_mapping params with num_kv_heads to attention kernel. (#1997)

2023-12-10 10:12:53 -08:00

models

[Minor] Add comment on skipping rope caches (#2004)

2023-12-10 10:04:12 -08:00

parallel_utils

Correct comments in parallel_state.py (#1818)

2023-11-28 10:19:35 -08:00

__init__.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

input_metadata.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

model_loader.py

Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836)

2023-12-07 23:16:52 -08:00

sampling_metadata.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

utils.py

TP/quantization/weight loading refactor part 2 - Refactor quantized linear logic and extend quantization support to all models (#1622)

2023-11-15 22:50:41 -08:00

weight_utils.py

[BugFix] Fix a bug in loading safetensors (#1732)

2023-11-20 15:51:18 -08:00