github-featured/alibaba--mnn
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity
2,521 Commits 107 Branches 115 Tags
edf9165248cc421e986851d3bb1aea404b22adbb
Commit Graph

33 Commits

Author SHA1 Message Date
MNNSyncBot edf9165248 Merge pull request #4076 from jxt1234/feature/smallmodel_opt 
Feature/smallmodel opt

GitOrigin-RevId: 5610add6e64c6d49f8b984d0d744c85f206f2be7
 2025-12-23 16:37:46 +08:00
MNNSyncBot a92edc9b42 Project import generated by Copybara. 
GitOrigin-RevId: fd90884f44c381932e3de8224bc69a0c327a3344
 2025-12-23 16:31:11 +08:00
MNNSyncBot b969229773 Merge pull request #4076 from jxt1234/feature/smallmodel_opt 
Feature/smallmodel opt

GitOrigin-RevId: 5610add6e64c6d49f8b984d0d744c85f206f2be7
 2025-12-23 12:42:24 +08:00
MNNSyncBot 3d53ad1654 Project import generated by Copybara. 
GitOrigin-RevId: f936e7dcb1d1dbef608b5a01ad46ce1da8fca7de
 2025-12-23 12:39:29 +08:00
jxt1234 ffed9d7313 Tools:Feature: Support dump per op cost for ModuleBasic 2025-12-22 16:04:52 +08:00
zhaode.wzd f31132f9d7 [Sync] Update MNN to 3.3.1 and Sync Internal Improvements 
- Version: Upgrade to 3.3.1.
- LLM: Refactor with Transformer-like config/model/tokenizer; optimize Tokenizer load speed; enhance KV Cache (mmap, disk storage, prefix cache); fix LoRA and VL model bugs.
- CPU/SME: Support SME/SME2 instructions and mixed NEON/SME multi-threading; optimize RVV intrinsics and FP32 depth-wise kernels.
- Metal/OpenCL: Support Metal KV Cache mmap and GPU family identification; refactor OpenCL Loop operators and fix offset bugs.
- QNN/Android: Optimize QNN build/conversion; update Reranker API; fix Android packaging and SO loading issues.
- General: Fix compilation for Arm32/Win/MinGW; update gitignore and expose public symbols; revert StrideSliceWrite behavior.
 2025-12-19 09:45:24 +08:00
zhaode.wzd 55a59a7ebc [MNN:Sync] Sync Internal reranker, gpt-oss. 2025-08-08 12:24:23 +08:00
yanzhang f699ca2842 Replace the KleidiAI macro with the hint config 
Signed-off-by: yanzhang <yanzhang.wang@arm.com>
Change-Id: I9dcc4f68e1e67a11266b66589006650b197cde1e
 2025-08-04 15:58:03 +08:00
xiaying db0f559f9d MNN:Sync: Sync Internal 3.2.2 2025-07-23 14:33:57 +08:00
Jules c018eacc00 refactor cpuids setting from BackendConfig to HintMode 2025-07-18 09:42:59 +00:00
Jules d87ebbe227 bind cpuIds 2025-07-16 05:41:41 +00:00
xiaying e5e7fccd99 MNN:Sync: Sync Internal 3.2.1 2025-06-17 11:08:21 +08:00
zhaode.wzd a019d971ad [MNN:Sync] Sync Internal 3.1.4. 2025-05-08 12:39:44 +08:00
xiaying c0247c6998 MNN:Sync: Sync Internal 3.1.1 2025-03-12 11:35:16 +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 5b901d9d87 MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
xiaying 1effb0c9e5 MNN:Sync: Sync Internal 2.9.5 2024-09-12 12:57:57 +08:00
xiaying c6f25cafc6 MNN:Sync: Sync Internal 2.9.3 2024-07-22 20:51:06 +08:00
xiaying 65ec0ea406 MNN:Sync: Fix bug for llama2/llama3 attention fuse, refract llm usage 2024-06-15 15:39:59 +08:00
xiaying 5b19cbbbf1 [MNN:Sync] Sync Internal 2.9.1 2024-06-03 20:09:34 +08:00
xiaying 7cad2ee83f MNN:Sync Sync Internal 2.9.0 2024-05-11 19:17:02 +08:00
xiaying 5895243607 [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
zhaode.wzd 3b978d9d16 [MNN:Sync] Sync Internal 2.8.1 2023-12-27 17:26:44 +08:00
zhaode.wzd 387775be2a [MNN:Sync] Sync Internal 2.8.0 2023-12-04 11:19:10 +08:00
xiaying 84d6bd75ae [MNN:Sync] Sync Internal 2.6.2 2023-07-31 14:24:48 +08:00
xiaying 39e2e7e45f [MNN:Sync] Sync Internal Gitlab 2.4.3 2023-04-18 18:54:46 +08:00
xiaying f26fc2efd8 [MNN:Sync] Sync 2.4.2 2023-04-11 11:12:00 +08:00
xiaying d46b6b998d [MNN:Sync] Sync Internal 2.3.0 2022-12-30 15:18:58 +08:00
xiaying d3ffdf4229 [MNN:Sync] Sync internal gitlab 2022-06-24 18:30:05 +08:00
xiaying aeaac3fde3 [MNN:Sync] Sync internal gitlab 2022-06-10 10:39:50 +08:00
xiaying 1b626d72c3 [MNN:Sync] Sync internal gitlab 2022-01-04 10:50:40 +08:00
xiaying 69dba73dc7 [MNN:Sync] Sync internal gitlab 
Main Feature:
1. Add OpenCV API and Numpy API Support
2. Protobuf move into MNN
3. Add more op for torchscript convert
4. Add recompute to speed up geometry compute
5. Add ModuleBasic Test
 2021-11-30 10:10:53 +08:00