Skip to content

Issues: intel/graph-compiler

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

54 Open 125 Closed
54 Open 125 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

ConvertGPUXToSPIRV fail to lower the dynamic matmul correctly bug Something isn't working
#403 opened Oct 30, 2024 by zhczhong
Endless loop in the pass linalg-to-xegpu bug Something isn't working
#402 opened Oct 30, 2024 by zhczhong
1
Properly handle SLM memory at linalg-to-xegpu pass GPU
#394 opened Oct 28, 2024 by dchigarev
@dchigarev
Build via compile.sh documentation Improvements or additions to documentation
#391 opened Oct 25, 2024 by akroviakov
Create a function test suite for OV out of OV ops translations
#388 opened Oct 21, 2024 by kurapov-peter 0.2 GPU OpenVino Integration
@zhczhong
Python tests misconfiguration for gc-check target bug Something isn't working
#386 opened Oct 21, 2024 by kurapov-peter
Windows build
#385 opened Oct 21, 2024 by kurapov-peter
OV single matmul case fail
#382 opened Oct 16, 2024 by WangJialei-A
@WangJialei-A @dchigarev
1
Single matmul runtime segfault due to K dimension out of bound access bug Something isn't working
#378 opened Oct 14, 2024 by yifeizh2 0.1 CPU - Matmul functionnality support
@yifeizh2
2
memref.alloc() on dynamic shape tensor cannot be successfully lowered
#377 opened Oct 11, 2024 by yifeizh2 0.1 CPU - Llama functionnality support
@yifeizh2
1
Add more test to dashboard
#374 opened Oct 8, 2024 by lmontigny 0.3 CI/CD
@WangJialei-A
Cmake-fetching GC fails bug Something isn't working
#371 opened Oct 7, 2024 by kurapov-peter 0.1 CPU - General
Pass DLTI for GPU from OV GPU performance Speedup expected
#369 opened Oct 4, 2024 by kurapov-peter 0.2 GPU OpenVino Integration
@AndreyPavlenko
[LinalgToXeGPU] Support linalg.matmul_transpose_a
#361 opened Sep 25, 2024 by dchigarev 0.2 GPU Upstream XeGPU
one-shot-bufferize pass generates memref.alloc()s in GPU kernels code and breaks the pipeline bug Something isn't working
#360 opened Sep 25, 2024 by zhczhong 0.2 GPU Downstream IMEX
@dchigarev
5
Merge cost model
#359 opened Sep 24, 2024 by lmontigny 0.1 CPU - Matmul functionnality support
GC check fail with clang & release build bug Something isn't working
#355 opened Sep 24, 2024 by WangJialei-A 0.1 CPU - General
@WangJialei-A
No verbose on correctness check script ci Continuous integration and automation ready to review validation
#352 opened Sep 23, 2024 by WangJialei-A 0.4 [Validation] benchgc
1
@xurui1995
1
Allow for passing an allocator to the GPU pipeline GPU
#345 opened Sep 16, 2024 by kurapov-peter 0.2 GPU OpenVino Integration
Add an option for insert gpu allocs to treat allocations as gpu-native
#344 opened Sep 16, 2024 by kurapov-peter 0.2 GPU Upstream XeGPU
@zhczhong
1
Constant cache manager and runtime pipeline
#341 opened Sep 14, 2024 by niuxiaog 0.1 CPU - General
1
@niuxiaog
[IterativeTilingAndFusionPass] Wrap linalg.ops in a loop even if the shape is smaller than min tiling size
#332 opened Sep 10, 2024 by dchigarev 0.2 GPU Upstream XeGPU
1
Convert large vector to physical register vector CPU
#331 opened Sep 10, 2024 by BRUCE11111 0.1 CPU - General
@BRUCE11111
1
add tuner mode for BenchGC to support auto-tuning CPU enhancement New feature or request ready to review
#330 opened Sep 10, 2024 by xurui1995 0.4 [Validation] benchgc
1
@xurui1995
1
Nightly Performance Result
#322 opened Sep 5, 2024 by github-actions bot
ProTip! no:milestone will show everything without a milestone.