liddk1121 1b54a2831e Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00

..

ernie4_5_vl

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

__init__.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

deepseek_v3.py

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

ernie4_5_moe.py

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

ernie4_5_mtp.py

Extract eh_proj Layer from ParallelLMHead for MTP to Avoid Weight Transposition Issue (#2707)

2025-07-04 14:15:04 +08:00

model_base.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

qwen2.py

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

qwen3.py

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

qwen3moe.py

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

tp_utils.py

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00

utils.py

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00