chen 76649b45c1 [Optimization] compulte real max_logprobs in batch (#5430)

2025-12-09 14:15:05 +08:00

..

__init__.py

…

dcu_model_runner.py

…

dcu_worker.py

…

eplb.py

…

experts_manager.py

…

gcu_model_runner.py

[Models] Add forward_meta to moe models' forward function (#5138)

2025-12-04 13:26:58 +08:00

gcu_worker.py

…

gpu_model_runner.py

[Optimization] compulte real max_logprobs in batch (#5430)

2025-12-09 14:15:05 +08:00

gpu_worker.py

…

hpu_model_runner.py

[Intel HPU] fix bug about RP 5138 (#5380)

2025-12-05 11:33:29 +08:00

hpu_worker.py

…

iluvatar_model_runner.py

…

iluvatar_worker.py

…

metax_model_runner.py

[Metax] optimize mla attention (#5258)

2025-12-09 11:18:19 +08:00

metax_worker.py

[Metax] optimize mla attention (#5258)

2025-12-09 11:18:19 +08:00

model_runner_base.py

[Feature] support chunked moe (#4575)

2025-12-01 15:17:18 +08:00

output.py

fix logprobs (#5335)

2025-12-04 10:38:51 +08:00

tbo.py

[Feature] support Two batch overlap, mainly used in Prefill (#5078)

2025-12-05 14:58:50 +08:00

worker_base.py

…

worker_process.py

[New][RL] Support Rollout Routing Replay (#5405)

2025-12-05 22:06:26 +08:00

xpu_model_runner.py

[XPU] [Optimization] [EP] EP communication optimization. (#5145)

2025-12-05 10:03:45 +08:00

xpu_worker.py

[xpu] support mtp for xpu(mix) (#5274)

2025-12-01 11:03:14 +08:00