Cheng Wan 6410800af9 [unified-memory] Enable prefill cuda-graph capture (#37418)

2026-09-13 19:17:19 -07:00

..

diffusion

[diffusion] fix: recover ipc jit initialization after interrupted builds (#39034)

2026-09-11 19:34:09 +08:00

disaggregation

[unified-memory] PD disaggregation for every unified pool shape (#37506)

2026-09-13 19:16:43 -07:00

dsv4

[CI] Trim DSV4 trtllm B200 tests (#39013)

2026-09-11 01:04:16 -07:00

gdn

Fix Qwen3.5 GDN multi-item scoring (#33922)

2026-09-09 22:30:39 -07:00

hicache

[HiCache][LoRA] Isolate storage pages by extra key (#38577)

2026-09-12 18:18:14 +08:00

lora

[LoRA] Support MoE in full and breakable prefill CUDA graphs (#38578)

2026-09-11 14:40:02 -07:00

models

[unified-memory] Enable prefill cuda-graph capture (#37418)

2026-09-13 19:17:19 -07:00

models_large

[Config] Retire get_global_server_args, and clear the deprecated flags that have a replacement (#38375)

2026-09-08 16:42:12 -07:00

speculative

feat: support TP>1 Domino rollout for DFlash V2 (#37069)

2026-09-11 18:51:11 -07:00

xpu

Inference Support Mamba 2 and 1 (#34556)

2026-09-12 20:51:18 +08:00