github-featured/alibaba--mnn
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity
3,002 Commits 107 Branches 115 Tags
master
Commit Graph

140 Commits

Author SHA1 Message Date
MNNSyncBot 64f4aee605 [MNN:Bugfix] fix QNN windows msvc compile error. 
Link: https://code.alibaba-inc.com/AliNN/AliNNPrivate/codereview/27470555
* [MNN:Bugfix]解决QNN后端在windows msvc编译时出错的bug
GitOrigin-RevId: 69c65f0dd88b4d4f66601ac5f786b436adab2f70
 2026-05-19 16:55:21 +08:00
MNNSyncBot 35ba41e91b [MNN:Bugfix] fix MNN2QNNModel compile error in Windows. 
GitOrigin-RevId: abb13f0f7f87b46cae79c3c283fae09c461cae4a
 2026-05-08 20:10:38 +08:00
MNNSyncBot d79be7f94d [QNN:Bugfix] Fix vision model errors and abnormal quant params; add Qwen3.5 support 
GitOrigin-RevId: 36c983b957bf09de44400548710233355be286c8
 2026-05-08 13:35:23 +08:00
MNNSyncBot ba76938ec0 [LLM:Feature] Add gemma4 model support (text + vision + audio) 
Discussed-in: Merge-Request 26743543 , URL: https://code.alibaba-inc.com/AliNN/AliNNPrivate/codereview/26743543
GitOrigin-RevId: 30953b120a260d8fae4961f1661970927f642d10
 2026-04-09 19:52:07 +08:00
YinHanke 5889d95ab6 [LLM:Bugfix] Fix Qwen3-Embedding QNN export pipeline (#4216) 2026-03-10 17:34:50 +08:00
jxt1234 080bb3182b [QNN:Feature] Support QNN Attention for LLM with max_history_token and fix QNN op bugs (#4174) 2026-03-09 14:07:37 +08:00
MNNSyncBot 96915f6a6a Merge pull request #4098 from jxt1234/feature/support_reduce_byop 
Tools:Feature: Support Collect Op list from model and prue_mnn_ops fr…
GitOrigin-RevId: 98dcb294b97d01203cd0857226f09df27854c601
 2026-01-08 09:38:29 +08:00
MNNSyncBot d9b8afcfe1 Merge pull request #4083 from jxt1234/feature/bugfix 
Feature/bugfix

GitOrigin-RevId: d2bdbcaea51476ba14d63a4b970c8086296983f6
 2026-01-08 09:37:05 +08:00
MNNSyncBot b3325f3740 Merge pull request #4082 from jxt1234/feature/smallconvolutionwithgroupopt 
Turn small group convolution to depthwise

GitOrigin-RevId: 76125d130499262de99e6e78c3182a734f69a899
 2026-01-08 09:35:43 +08:00
MNNSyncBot 12d7623b8d Merge pull request #4098 from jxt1234/feature/support_reduce_byop 
Tools:Feature: Support Collect Op list from model and prue_mnn_ops fr…
GitOrigin-RevId: f7b3ff63717815c78425e8920570172b1655bb30
 2026-01-07 10:41:58 +08:00
MNNSyncBot 17c52757d0 Merge pull request #4083 from jxt1234/feature/bugfix 
Feature/bugfix

GitOrigin-RevId: acd71efe9b5ece4a3d14f7fff346349250c3e515
 2026-01-07 10:40:40 +08:00
MNNSyncBot c7a20dfe73 Merge pull request #4082 from jxt1234/feature/smallconvolutionwithgroupopt 
Turn small group convolution to depthwise

GitOrigin-RevId: 5f7342c97adffa06cbdeda49b287262f1c076922
 2026-01-07 10:39:18 +08:00
jxt1234 dcf87d176d Tools:Feature: Support Collect Op list from model and prue_mnn_ops from the info 2026-01-06 19:20:49 +08:00
MNNSyncBot b6b1a64bf8 Merge pull request #4083 from jxt1234/feature/bugfix 
Feature/bugfix

GitOrigin-RevId: 2d6322847819ddb71fb304325be4a36e10be2bb6
 2025-12-30 18:05:35 +08:00
MNNSyncBot 71ded12ca9 Merge pull request #4082 from jxt1234/feature/smallconvolutionwithgroupopt 
Turn small group convolution to depthwise

GitOrigin-RevId: ee2463d235e48d2e2b850a34f0c8c8258df155b0
 2025-12-30 18:04:22 +08:00
jxt1234 bddc28fbf0 MNN:Bugfix: Fix bug for CPUAttention with input size == 3 2025-12-30 14:45:18 +08:00
MNNSyncBot 36c176b3a3 Merge pull request #4076 from jxt1234/feature/smallmodel_opt 
Feature/smallmodel opt

GitOrigin-RevId: b70053578dc772bc05f432e80ff689fdb3bbd938
 2025-12-26 16:31:27 +08:00
MNNSyncBot f15a3d572f Project import generated by Copybara. 
GitOrigin-RevId: 804774d5836618d85384e4f0ce815ec94dec02de
 2025-12-26 16:26:20 +08:00
MNNSyncBot a2745676aa Merge pull request #4076 from jxt1234/feature/smallmodel_opt 
Feature/smallmodel opt

GitOrigin-RevId: 99ed7ba5bc1eefac17236785e3fadde5d0f372e8
 2025-12-26 16:25:45 +08:00
MNNSyncBot f939b32f23 Project import generated by Copybara. 
GitOrigin-RevId: 59c693e6995609611fb7197f2288cc929370bdd6
 2025-12-26 16:22:56 +08:00
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
xiaying 2198362a1b Bugfix: MNN2QNNModel, not add audio.so, smooth quant with vl 2025-11-06 16:49:42 +08:00
xiaying 1ca62a02f7 MNN:Sync: Sync Internal 3.3.0 2025-10-31 11:29:14 +08:00
xiaying 7fde7c7079 MNN:Sync: Sync Internal 3.2.4 2025-09-22 23:05:26 +08:00
xiaying 318a3de860 MNN:Sync: Sync Internal 3.2.3 2025-08-22 18:04:08 +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
xiaying 90671dcc64 OpenCL:Bugfix: Fix bug for compile in windows for OpenCLProgramBuildTest 2025-06-05 16:46:10 +08:00
xiaying 09b6cd9862 MNN:Sync: Sync 3.2.0 2025-06-05 15:15:29 +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
xiaying e9c3296942 MNN:Sync: Sync Internal 3.1.2 2025-03-27 11:30:13 +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 3b6ddc0341 MNN:Sync: Sync Internal 3.0.5 2025-02-12 11:14:19 +08:00
若遗 d14e5fc19f restore Files deleted by mistake 2025-01-24 10:42:02 +08:00
若遗 4e91694590 增加 readme 修复编译问题 2025-01-23 19:41:42 +08:00
若遗 189d113840 Merge remote-tracking branch 'remotes/origin/master' 
# Conflicts:
#	CMakeLists.txt
 2025-01-23 16:14:19 +08:00
xiaying 766815282f MNN:Sync: Sync Internal 3.0.4 2025-01-22 16:28:36 +08:00
若遗 db85207f63 add pc commandline mls 2025-01-17 21:36:14 +08:00