Juncai 36822fa49c [PD Disaggregation] remove splitwise deployment on single node and refine the code (#4891) ...

* remove splitwise deployment on single node and refine the code

* up

* up

* up

* add test

* up

2025-11-14 09:56:53 +08:00

..

images

Update sparse attn documentation (#3954)

2025-09-08 12:23:18 +08:00

chunked_prefill.md

[Docx] add language (en/cn) switch links (#4470)

2025-10-17 15:47:41 +08:00

data_parallel_service.md

[Docx] add language (en/cn) switch links (#4470)

2025-10-17 15:47:41 +08:00

disaggregated.md

[PD Disaggregation] remove splitwise deployment on single node and refine the code (#4891)

2025-11-14 09:56:53 +08:00

early_stop.md

[Docx] add language (en/cn) switch links (#4470)

2025-10-17 15:47:41 +08:00

graph_optimization.md

[Executor] Default use CUDAGraph (#3594)

2025-10-21 14:25:45 +08:00

load_balance.md

[Docx] add language (en/cn) switch links (#4470)

2025-10-17 15:47:41 +08:00

logits_processor.md

[Feature] support logits processors (#4515)

2025-10-29 00:08:53 +08:00

multi-node_deployment.md

[Feature] [PD] add simple router and refine splitwise deployment (#4709)

2025-11-06 14:56:02 +08:00

plas_attention.md

[Docx] add language (en/cn) switch links (#4470)

2025-10-17 15:47:41 +08:00

plugins.md

[Docx] add language (en/cn) switch links (#4470)

2025-10-17 15:47:41 +08:00

prefix_caching.md

[Docx] add language (en/cn) switch links (#4470)

2025-10-17 15:47:41 +08:00

reasoning_output.md

[Docs] add ERNIE-4.5-VL-28B-A3B-Thinking instruction (#4937)

2025-11-11 10:43:44 +08:00

sampling.md

[Docx] add language (en/cn) switch links (#4470)

2025-10-17 15:47:41 +08:00

speculative_decoding.md

[Docx] add language (en/cn) switch links (#4470)

2025-10-17 15:47:41 +08:00

structured_outputs.md

[Docx] add language (en/cn) switch links (#4470)

2025-10-17 15:47:41 +08:00

tool_calling.md

[Docs] add ERNIE-4.5-VL-28B-A3B-Thinking instruction (#4937)

2025-11-11 10:43:44 +08:00