Shangming Cai eb429b88a4 [PD] Respect sampling_params.max_new_tokens when PD disaggregation is activated (#7598) ...

Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>

2025-06-27 22:22:01 -07:00

..

base

[PD] Add different TP sizes support for no-MLA models (#6793)

2025-06-25 02:00:22 -07:00

common

Minor PD style fix (#7215)

2025-06-15 16:12:12 -07:00

fake

Minor PD style fix (#7215)

2025-06-15 16:12:12 -07:00

mooncake

[PD] Raise error for incompatible mooncake version and some minor fixes (#7527)

2025-06-25 18:55:24 -07:00

nixl

[PD][NIXL] Set is_sorted=False to fix NIXL_ERR_NOT_FOUND (#7330)

2025-06-26 10:39:39 -07:00

decode_schedule_batch_mixin.py

[PD] Transfer hidden states for mtp when disaggregation (#7242)

2025-06-19 11:22:47 -07:00

decode.py

[PD] Respect sampling_params.max_new_tokens when PD disaggregation is activated (#7598)

2025-06-27 22:22:01 -07:00

kv_events.py

feat: add dp-rank to KV events (#6852)

2025-06-04 15:29:34 -07:00

launch_lb.py

PD Rust LB (PO2) (#6437)

2025-05-29 20:50:10 +08:00

mini_lb.py

Merge PDLB (Prefill-Decode Load Balancer) into SGLang Router (#7096)

2025-06-19 02:28:15 +08:00

prefill.py

[PD] Add different TP sizes support for no-MLA models (#6793)

2025-06-25 02:00:22 -07:00

utils.py

[PD][Spec] Fix hidden state transfer for spec decode (#7516)

2025-06-25 00:42:07 -07:00