kevin 8e4e3ff510 [Feature] support eplb in api_server (#4782) ...

* support eplb in api_server

* update code

* add eplb test case

* update eplb

* support tp+dp eplb

* update test cese

* update code

* update code

* fix bug

* update copilot review

* update test case name

2025-11-24 20:22:29 +08:00

..

ernie4_5_vl

support moe offline quant (#5142)

2025-11-24 18:59:18 +08:00

paddleocr_vl

[Optimization] default compile rdma, reduce cudagraph buffer size in mm, fix some config bug (#5121)

2025-11-20 17:19:47 +08:00

qwen2_5_vl

[Optimization] default compile rdma, reduce cudagraph buffer size in mm, fix some config bug (#5121)

2025-11-20 17:19:47 +08:00

__init__.py

[Feature] support pool (#3827)

2025-09-22 14:09:09 +08:00

adapters.py

fix the get_act_fn,_load_st_projector (#4824)

2025-11-06 16:13:35 +08:00

deepseek_v3.py

[Executor]move batch_id_per_token (#4853)

2025-11-14 15:38:48 +08:00

ernie4_5_moe.py

[Feature] support eplb in api_server (#4782)

2025-11-24 20:22:29 +08:00

ernie4_5_mtp.py

refactor pt loading (#4532)

2025-11-11 21:30:39 +08:00

ernie_vl_rm.py

[Optimization] default compile rdma, reduce cudagraph buffer size in mm, fix some config bug (#5121)

2025-11-20 17:19:47 +08:00

glm4_moe.py

refactor pt loading (#4532)

2025-11-11 21:30:39 +08:00

gpt_oss.py

refactor pt loading (#4532)

2025-11-11 21:30:39 +08:00

interfaces_base.py

Optimizing the performance of think length limit using custom operators (#4279)

2025-10-20 21:09:13 +08:00

model_base.py

Optimizing the performance of think length limit using custom operators (#4279)

2025-10-20 21:09:13 +08:00

qwen2_rm.py

add qwen-2.5-7B-PRM/ernie-rm (#4319)

2025-10-20 15:31:03 +08:00

qwen2.py

[RL]Resolve shape mismatch problems in RL-related modules (#5032)

2025-11-19 11:12:48 +08:00

qwen3.py

[RL]Resolve shape mismatch problems in RL-related modules (#5032)

2025-11-19 11:12:48 +08:00

qwen3moe.py

refactor pt loading (#4532)

2025-11-11 21:30:39 +08:00

tp_utils.py

Supports DP+TP+EP hybrid parallel deployment strategy (#3489)

2025-08-26 00:04:01 -07:00

utils.py

delete useless code (#4544)

2025-10-23 13:40:34 +08:00