Commit Graph

21 Commits

Author SHA1 Message Date
hzx 664ee20e2b add pd disaggregation and separate acceleration on CPU backend 2025-05-28 19:50:53 +08:00
zhaode.wzd bd36a3f749 [MNN:Sync] Sync internal:
1. SmolVLM, FastVLM support.
    2. QNN backend init.
    3. Qwen3 MoE support.
    4. Speculative decodeing init.
    5. Some bugfix.
2025-05-23 15:24:18 +08:00
zhaode.wzd a019d971ad [MNN:Sync] Sync Internal 3.1.4. 2025-05-08 12:39:44 +08:00
xiaying 0769b81b58 MNN:Sync: Sync Internal 3.1.3 2025-04-28 11:50:24 +08:00
hzx 42d2e3a0b4 glm-4 rope_ratio export bug is fixed. nested template problem is fixed 2025-03-17 21:44:35 +08:00
xiaying c0247c6998 MNN:Sync: Sync Internal 3.1.1 2025-03-12 11:35:16 +08:00
zhaode.wzd d9a6ce3ac1 [MNN:Sync] Sync Internal 3.1.0. 2025-02-24 11:44:27 +08:00
xiaying b935891ece MNN:Sync: Sync a few bugfix, add qwen2.5-vl support 2025-02-17 19:11:14 +08:00
xiaying 3b6ddc0341 MNN:Sync: Sync Internal 3.0.5 2025-02-12 11:14:19 +08:00
xiaying 766815282f MNN:Sync: Sync Internal 3.0.4 2025-01-22 16:28:36 +08:00
xiaying da4023c222 MNN:Sync: Sync Interal 3.0.2 2024-12-19 20:34:17 +08:00
hzx 36129453f6 fix mps, onnx-slim bugs 2024-12-04 10:33:23 +08:00
hzx 9f116b89bd merge MNN-3.0.1 2024-12-02 22:35:36 +08:00
xiaying 809bff1b30 MNN:Sync: Sync Internal 3.0.1 2024-12-02 10:12:08 +08:00
hzx 5079f7eaf5 not runnable yet 2024-11-20 11:43:26 +08:00
xiaying 5b901d9d87 MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
hzx 656dc18695 resolve conflicts 2024-10-29 19:38:29 +08:00
hzx 93656a3a3a first commit for Sampler 2024-10-29 19:32:47 +08:00
xiaying 860fceb3ab MNN:Sync: Sync Internal 2.9.6 2024-10-14 19:26:28 +08:00
雁行 9471df1f94 [Llm:Feature] Support Qwen2-VL export and inference. 2024-09-12 20:19:02 +08:00
xiaying 1effb0c9e5 MNN:Sync: Sync Internal 2.9.5 2024-09-12 12:57:57 +08:00