enginex-c_series-vllm/model_executor at 24fab12b2f3bfdc8312e6639672a68b308bffcec - enginex-c_series-vllm - Gitea: Git with a cup of tea

sunjichen/enginex-c_series-vllm

forked from EngineX-MetaX/enginex-c_series-vllm

Files

History

wangjing 24fab12b2f [qwen3-omni] Add Qwen3-Omni moe thinker

2025-10-09 17:51:14 +08:00

..

guided_decoding

[gpt-oss] Add gpt-oss bf16 support

2025-08-15 03:44:05 +00:00

[qwen3-omni] Add Qwen3-Omni moe thinker

2025-10-09 17:51:14 +08:00

[gpt-oss] Add gpt-oss bf16 support

2025-08-15 03:44:05 +00:00

[qwen3-omni] Add Qwen3-Omni moe thinker

2025-10-09 17:51:14 +08:00

__init__.py

[gpt-oss] Add gpt-oss bf16 support

2025-08-15 03:44:05 +00:00

custom_op.py

[gpt-oss] Add gpt-oss bf16 support

2025-08-15 03:44:05 +00:00

parameter.py

[gpt-oss] Add gpt-oss bf16 support

2025-08-15 03:44:05 +00:00

pooling_metadata.py

[gpt-oss] Add gpt-oss bf16 support

2025-08-15 03:44:05 +00:00

sampling_metadata.py

[gpt-oss] Add gpt-oss bf16 support

2025-08-15 03:44:05 +00:00

utils.py

[gpt-oss] Add gpt-oss bf16 support

2025-08-15 03:44:05 +00:00