Skip to content

Pull requests: intel/torch-xpu-ops

New pull request New
89 Open 1,267 Closed
89 Open 1,267 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[CI] Port ut test_decomp.py from pytorch
#2262 opened Oct 31, 2025 by libohao1201 Loading…
8
add CMAKE_SYCL_COMPILER_LAUNCHER for sccache.
#2260 opened Oct 31, 2025 by xuhancn Loading…
Migrate test_utils, test_schema_check for xpu and add checkpoint.py f…
#2259 opened Oct 31, 2025 by shangerxin Loading…
10
Add Float8_e8m0fnu support for copy
#2258 opened Oct 31, 2025 by CuiYifeng Loading… PT2.10
4
enable more test classes and cases in test_ops_xpu.py
#2256 opened Oct 31, 2025 by daisyden Loading…
2
port test_sparse and test_sparse_csr for Intel GPU
#2252 opened Oct 31, 2025 by wincent8 Loading…
Fix failing ProcessGroupXCCL tests
#2231 opened Oct 28, 2025 by frost-intel Loading…
1
3
[CI] Update UT summary format
#2226 opened Oct 28, 2025 by RUIJIEZHONG66166 Loading…
[CI] Add CI gating based on E2E performance test results check
#2224 opened Oct 28, 2025 by mengfei25 Loading…
1
Bump minimal supported Python version from 3.8 to 3.10
#2221 opened Oct 27, 2025 by Silv3S Loading…
1
[CI] Port test/functorch/test_ops.py and test/test_unary_ufuncs.py from pytorch module: ut
#2210 opened Oct 23, 2025 by zxd1997066 Loading…
[WIP] Fused RMSNorm implementation
#2205 opened Oct 22, 2025 by guangyey • Draft
1
4
Support FP8 in op flip, index_put, and index.Tensor
#2190 opened Oct 20, 2025 by chunhuanMeng Loading… PT2.10
6
set small grf for dynamic cast kernel_optimization
#2185 opened Oct 16, 2025 by jianyizh Loading…
5
port cuda specific case with hook
#2184 opened Oct 16, 2025 by daisyden Loading…
1
2
Fix pdist numerical issue on large input size
#2181 opened Oct 15, 2025 by Kanya-Mo Loading…
1
2
[CI]Enable pt2e fp16 acc test
#2176 opened Oct 15, 2025 by kaileiyx Loading…
add time event support
#2175 opened Oct 15, 2025 by Chao1Han Loading…
5
Run torch.special.logit in reduced precision for bf16/f16 inputs
#2156 opened Oct 10, 2025 by Silv3S Loading…
7
Enable FP8 compare_xpu
#2154 opened Oct 10, 2025 by yucai-intel Loading…
2
Enable FP8 concat_xpu and where_xpu
#2152 opened Oct 10, 2025 by yucai-intel Loading… PT2.10
6
fix Windows cmake for BUILD_SEPARATE_OPS
#2147 opened Oct 9, 2025 by xuhancn Loading…
Enable FP8 add/sub/mul/div
#2145 opened Oct 9, 2025 by CuiYifeng • Draft
Rebase dev/sycl-free-func
#2141 opened Oct 9, 2025 by fengyuan14 Loading…
use SYCL queue.memcpy instead of copy kernel
#2095 opened Sep 22, 2025 by jianyizh Loading…
2
ProTip! no:milestone will show everything without a milestone.