yinwei a64c0408b9 [XPU]Fix w4a8 precision bug && rollback moe algo (#4463) ...

* fix w4a8 precision bug

* add env

* code stype check

2025-10-17 18:27:53 +08:00

..

DCU

mv test to tests (#4129)

2025-09-16 20:45:40 +08:00

EB_Lite

[CI] enhance clean port and add waiting time (#4152)

2025-09-17 20:31:49 +08:00

EB_Lite_with_adapter

[CI] Fix partial instability issues (#4461)

2025-10-17 14:17:06 +08:00

EB_VL_Lite

Support limit thinking lengths (#4069)

2025-09-25 19:55:56 +08:00

ERNIE_0dot3B

[Feature] add config api (#4254)

2025-09-26 11:21:02 +08:00

GCU

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

GLM-45-AIR

[CI] Fix partial instability issues (#4461)

2025-10-17 14:17:06 +08:00

iluvatar_UT

[Iluvatar GPU] Optimize attention performance and fix moe load ckpt error (#3651)

2025-09-22 21:13:59 +08:00

Qwen2_5_VL

[Model] Qwen2.5VL support --use-cudagraph and unit testing (#4087)

2025-09-24 19:45:01 +08:00

Qwen2-7B-Instruct_offline

Support offline inference with streaming output (#4071)

2025-09-15 10:27:03 +08:00

Qwen2-7B-Instruct_serving

[CI] enhance clean port and add waiting time (#4152)

2025-09-17 20:31:49 +08:00

Qwen3-MoE

[CI] enhance clean port and add waiting time (#4152)

2025-09-17 20:31:49 +08:00

utils

[Test]add glm45_air logprob test and rollout model (#4175)

2025-09-23 21:06:07 +08:00

XPU_45T

[XPU]Fix w4a8 precision bug && rollback moe algo (#4463)

2025-10-17 18:27:53 +08:00