Hexagon 后端【高通NPU直接编程支持】 - #4633
Merged
Merged
Conversation
Qxinyu
approved these changes
Jul 21, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
qwen3-0.6b 8gen4 (v79)
Block64 sym
性能测试结果
测试设备: SM8750 (骁龙 8 Elite), Hexagon v79
模型: Qwen3-0.6B (4-bit 对称量化, block64, C4)
测试工具: llm_bench
表 1: SDK 5.x vs SDK 6.x 编译性能对比
结论: 两个 SDK 版本编译的 DSP skeleton 性能基本一致,差异在误差范围内。
表 2: Qwen3-0.6B 三后端性能对比
结论: Hexagon NPU 在 prefill 上优势最大 (7.9x),OpenCL GPU 次之 (4.4x)。CPU 在 decode 上最优。