weizhoublueandweizhoublue b6bdc5997f Fix: NPU AR model runner prefix cache key flattening (#3568) ...

Signed-off-by: weizhoublue <weizhoublue@github.com>
Signed-off-by: weizhou.lan@daocloud.io <weizhou.lan@daocloud.io>
Co-authored-by: weizhoublue <weizhoublue@github.com>

2026-05-13 08:22:48 +00:00

..

models

[NPU] Upgrade to v0.20.0 & align with GPU model runner (#3325)

2026-05-04 22:38:43 +08:00

quant

support online FP8 quantization for FA on NPU #2236 (#2640)

2026-05-13 11:46:00 +08:00

stage_configs

[Config] Add HunyuanImage3 deploy configs (#3172)

2026-05-11 22:49:19 +08:00

worker

Fix: NPU AR model runner prefix cache key flattening (#3568)

2026-05-13 08:22:48 +00:00

__init__.py

[Hardware] Support platforms and plugin system (#774)

2026-01-28 22:12:52 +08:00

platform.py

[Diffusion][Attention] Support per-role attention backend via CLI (#2681)

2026-05-10 11:59:05 +08:00

profiler.py

[Refactor] Unify torch profiler for omni and diffusion models (#2099)

2026-03-24 15:25:52 +08:00