support deepseek on xpu #10060
Open
support deepseek on xpu #10060
+4,659
−145
Conversation
This file contains 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
|
Thanks for your contribution! |
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## develop #10060 +/- ##
===========================================
- Coverage 50.39% 50.15% -0.24%
===========================================
Files 756 757 +1
Lines 121658 122553 +895
===========================================
+ Hits 61304 61469 +165
- Misses 60354 61084 +730 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
csrc/xpu/src/cmake_build.sh
Outdated
| # export XDNN_PATH=Paddle/build/third_party/xpu/src/extern_xpu/xdnn-ubuntu_x86_64/ # <path_to_xdnn> | ||
| # export XRE_PATH=Paddle/build/third_party/xpu/src/extern_xpu/xre-ubuntu_x86_64/ # <path_to_xre> | ||
| # export CLANG_PATH=xtdk-ubuntu_1604_x86_64 # <path_to_xtdk> | ||
| # export HOST_SYSROOT=/opt/compiler/gcc-8.2/bin/gcc # <path_to_gcc> | ||
|
|
||
| export XDNN_PATH=/opt/output/work_dir/paddle-deepseek/xpu_libs/xhpc/xdnn |
| const std::vector<int64_t>& seq_len_shape, | ||
| const std::vector<int64_t>& draft_tokens_shape, | ||
| const std::vector<int64_t>& seq_lens_encoder_shape) { | ||
| // std::cout << "wht --- GetPaddingOffsetV2InferShape" << std::endl; |
| prefix_lens_vp, // prefix_lens_vp | ||
| encoder_kv_lods_vp); // encoder_kv_lods_vp | ||
|
|
||
| // encoder 关键信息打印 |
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Outdated suggestions cannot be applied.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.
Before submitting
testsfolder. If there are codecov issues, please add tests cases first.PR types
New features
PR changes
Models | APIs
Description
Support deepseek on Kunlun XPU inference.
Support dynamic and static graphics.
Now, only MOE-ONLYINT8 quantization is supported (only MOE weights are quantized to int8, other weights are not quantized).