vllm-omni/vllm_omni/platforms/npu at codex/general-example-docs - vllm-omni - Gitea: Git with a cup of tea

anodyine/vllm-omni

0 Fork 0

Files

T

History

Zijun HuangandWeiQing Chen 93457f29ff [NPU][Quantization] Add RainFusion attention and INT8 online quantization for MiniMax H3 (#5706 )

Signed-off-by: Zijun Huang <zijunhua@usc.edu>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>

2026-08-06 14:15:21 +08:00

..

[CI failed] Revert "[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor" (#5777 )

2026-08-04 15:21:38 +00:00

[Bugfix][NPU] Fallback to BSND RoPE when Qwen3-TTS short-seq BNSD li… (#5608 )

2026-08-05 13:02:47 +08:00

[Bugfix][NPU] Fallback to BSND RoPE when Qwen3-TTS short-seq BNSD li… (#5608 )

2026-08-05 13:02:47 +08:00

omni_connectors

Yuanrong TransferEngine Connector for NPU (#3180 )

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

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

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

[NPU] upgrade to v0.26.0 (#5490 )

2026-07-29 11:21:04 +08:00

__init__.py

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

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

platform.py

[NPU][Quantization] Add RainFusion attention and INT8 online quantization for MiniMax H3 (#5706 )

2026-08-06 14:15:21 +08:00

profiler.py

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

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