4 people 37c11e6e4f [Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor (#5791) ...

Signed-off-by: sheenlin <sheenlin@tencent.com>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: sheenlin <sheenlin@tencent.com>
Co-authored-by: yurain <yurain26@users.noreply.github.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>

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

..

cuda

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

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

musa

[Hardware][MUSA] Complete Omni platform interfaces (#6058)

2026-08-11 12:46:42 +00:00

npu

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

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

rocm

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

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

xpu

[XPU][Bugfix] Make Omni AR async output path device-agnostic (#5569)

2026-08-19 20:06:33 -05:00

__init__.py

[Rebase] Rebase to vllm v0.24.0 (#4709)

2026-06-30 19:41:06 +08:00

interface.py

[Hardware][MUSA] Enable Qwen3-Omni ModelOpt FP8 inference (#5671)

2026-08-11 17:19:09 +08:00