Skip to content

Pull requests: intel/graph-compiler

New pull request New
22 Open 174 Closed
22 Open 174 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Transform][vector] lowering dynamic shape of tensor.pack to vector
#351 opened Sep 20, 2024 by BRUCE11111 Loading…
add thread local cache for brgemm
#350 opened Sep 20, 2024 by crazydemo Loading…
1
8
Minor build script enhancements
#349 opened Sep 19, 2024 by AndreyPavlenko Loading…
[LinalgToXeGPU] Lower linalg.matmul_transpose_b into xegpu.dpas GPU ready to review
#347 opened Sep 17, 2024 by dchigarev Loading…
1
3
Implemented GPU OpenCL runtime GPU
#343 opened Sep 14, 2024 by AndreyPavlenko Loading…
1
17
[Runtime] Constant cache manager and runtime pipeline CPU
#342 opened Sep 14, 2024 by niuxiaog Loading… 0.1 CPU - Llama functionnality support
1
Convert a subset of GPU dialect ops to the OpenCL GPU runtime calls GPU
#333 opened Sep 10, 2024 by AndreyPavlenko Loading…
12
[Transform] Hoist thread-local allocator within the nested parallel loops CPU ready to review
#283 opened Aug 26, 2024 by ciyongch Loading… 0.1 CPU - General
@ciyongch
26
Initial GPU pipeline ready to review
#202 opened Jul 30, 2024 by kurapov-peter Loading…
1
25
[RFC] Constant tensors caching pass documentation Improvements or additions to documentation ready to review
#183 opened Jul 24, 2024 by niuxiaog Loading… 0.1 CPU - General
8
[Experimental] Link TPP to experiment with GPU lowering in our project
#156 opened Jul 9, 2024 by LongshengDu • Draft
[Experimental][Transform] Split Compute Intensive Op
#154 opened Jul 5, 2024 by crazydemo Loading…
1
[Experimental] Update deep tiled matmul for Parallelize Graphs on multiple numa nodes
#153 opened Jul 5, 2024 by crazydemo Loading…
1
[RFC] Local tests for linalg.packed_matmul/linalg.packing_map implementations DO NOT MERGE upstream
#138 opened Jul 2, 2024 by LongshengDu • Draft
Transform: support sdpa to flash attention kernel conversion
#131 opened Jun 13, 2024 by yifeizh2 • Draft
1 of 3 tasks
1
5
[Linalgx] add bufferizable and tiling interface; reorganize file structure WIP work in progress
#130 opened Jun 11, 2024 by LongshengDu • Draft
Remove debug
#127 opened Jun 6, 2024 by leshikus Loading…
[Transform] mlir: named op layout propagation ready to review
#101 opened May 27, 2024 by yifeizh2 Loading…
1
[Transform][Vectorization] canonicalize vector with physical vector ready to review
#100 opened May 27, 2024 by BRUCE11111 Loading…
8 of 11 tasks
15
[Transforms] Add constant_tensors_folding pass CPU
#74 opened May 15, 2024 by niuxiaog Loading… 0.1 CPU - Llama functionnality support
4
[IR] Add easy-build for "if" and "for“ for general structured control flow Ops
#62 opened May 10, 2024 by Menooker Loading…
1
[MLIR][IR] Add easy-builder to simplify IR building in C++
#52 opened May 9, 2024 by Menooker Loading…
4
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.