Skip to content

Issues: intel/intel-xpu-backend-for-triton

Beta
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

242 Open 1,406 Closed
242 Open 1,406 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

Update CI runners to Agama 803.150 ci driver: lts
#4235 opened May 16, 2025 by pbchekin
@pbchekin
Update CI runners to Agama 1133 ci driver: rolling
#4234 opened May 16, 2025 by pbchekin
@pbchekin
[PyTorch][Inductor] TestSelectAlgorithm.test_convolution1 failed on LTS driver: lts upstream: pytorch
#4232 opened May 16, 2025 by anmyachev 1. [PT 2.8 Upstream] TorchInductor
@alexbaden
[Qunatization] Error on trying replace load with gather.
#4231 opened May 16, 2025 by Devjiu
1
[FlexAttention] There is an accuracy failure for the case test_weird_bias_batch:2_head:4_seq_len:256_headdim:16_dtype:float16_xpu
#4228 opened May 16, 2025 by chengjunlu
[FlexAttention] There is an accuracy failure for the case test_indirect_bias_batch:2_head:4_seq_len:256_headdim:16_dtype:float16_xpu
#4227 opened May 16, 2025 by chengjunlu
@chengjunlu
1
[FlexAttention] There is a accuracy failure for the case test_distinct_biases_batch:2_head:4_seq_len:256_headdim:16_dtype:float16_xpu
#4226 opened May 16, 2025 by chengjunlu
@chengjunlu
1
[TEST] Fix test_tensor_descriptor.py::test_mxfp8_mxfp4_matmul_tma
#4222 opened May 15, 2025 by whitneywhtsang
[TEST] Fix test_tensor_descriptor.py::test_tensor_descriptor_rank_reducing_load
#4221 opened May 15, 2025 by whitneywhtsang
torchdata==0.9.0 does not exist for Python 3.13 ci
#4216 opened May 15, 2025 by pbchekin
@pbchekin
[FlexAttention] There is a regression accuracy failure for the case test_njt_causal
#4211 opened May 15, 2025 by chengjunlu
@chengjunlu
1
[FlexAttention] There is a regression accuracy failure for the case test_builtin_score_mods_seqlen
#4210 opened May 15, 2025 by chengjunlu
@chengjunlu
1
[CI][Inductor] Parallel Inductor test runs
#4202 opened May 14, 2025 by vlad-penkin
@vlad-penkin
2
Remove run-time dependency on DLE for nightly wheels ci dependencies: pytorch
#4195 opened May 14, 2025 by pbchekin
@pbchekin
1
Use separate layout encodings for block io operations
#4192 opened May 14, 2025 by alexbaden
@alexbaden
[Intel] Add BF16 atomic_add support
#4191 opened May 13, 2025 by whitneywhtsang
[PyTorch][Inductor] TestInductorOpInfoXPU.test_comprehensive_asin_xpu_float32 tests: ut upstream: pytorch
#4185 opened May 13, 2025 by anmyachev
1
@anmyachev
9
[PyTorch][Inductor] GPUTests.test_upsample_bicubic2d_xpu failed tests: ut upstream: pytorch
#4184 opened May 13, 2025 by anmyachev
@whitneywhtsang
1
[Client CI][Client dev envs] Update oneAPI runtimes to 2025.1.1 ci dependencies: compiler dependencies: sycl runtime
#4173 opened May 12, 2025 by kwasd 7. CI and Tooling
@kwasd
[benchmarks][BMG] The profiling numbers don't match hw: bmg performance profiling reporting
#4172 opened May 12, 2025 by Egor-Krivov 7. CI and Tooling
@anmyachev
4
[TensorDescriptor] Enabling and performance codegen: mlir performance upstream: triton
#4170 opened May 11, 2025 by vlad-penkin 4. [Performance] Core
Consider enable SLPVectorization back codegen: mlir
#4167 opened May 11, 2025 by anmyachev 3. [Triton] Language and Runtime
4
Windows install documentation Improvements or additions to documentation hw: arc local builds windows
#4160 opened May 10, 2025 by fablevi 6. UX and packaging
@pbchekin
4
Investigate PyTorch inductor failures after Triton XPU pin update tests: ut upstream: pytorch
#4142 opened May 8, 2025 by anmyachev 1. [PT 2.8 Upstream] TorchInductor
@anmyachev @whitneywhtsang @etiotto
17
test_tensor_descriptor_store_nd doesn't verify for several data types and ndim codegen: mlir tests: ut
#4140 opened May 8, 2025 by etiotto 3. [Triton] Language and Runtime
ProTip! Exclude everything labeled bug with -label:bug.