XiongZhongwei 40dcfdbb43 [Perf][NPU] Enable native GQA & fused AddNorm for MiniMax-H3 encoder (#6040) ...

Signed-off-by: MarkPoloChina <1228479724@qq.com>
Signed-off-by: XiongZhongwei <1228479724@qq.com>

2026-08-26 09:14:05 +08:00

..

_310p

[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor (#5791)

2026-08-20 19:22:40 +00:00

layers

Fix npu moe registration (#6350)

2026-08-20 16:34:24 +00:00

models

[Perf][NPU] Enable native GQA & fused AddNorm for MiniMax-H3 encoder (#6040)

2026-08-26 09:14:05 +08:00

omni_connectors

Yuanrong TransferEngine Connector for NPU (#3180)

2026-05-20 14:51:33 +08:00

quant

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

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

worker

[Refactor][2/N Scheduler]Replace _FULL_PAYLOAD_INPUT_STAGES with a resolved stage transport capability. (#6149)

2026-08-25 15:24:59 +08:00

__init__.py

[MiniCPM-o][NPU] Enable MiniCPM-o Code2Wav NPUGraph replay (#5604)

2026-08-17 15:09:51 +08:00

graph_tools.py

[MiniCPM-o][NPU] Enable MiniCPM-o Code2Wav NPUGraph replay (#5604)

2026-08-17 15:09:51 +08:00

platform.py

[Perf][NPU] Enable native GQA & fused AddNorm for MiniMax-H3 encoder (#6040)

2026-08-26 09:14:05 +08:00

profiler.py

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

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