Skip to content

Pull requests: ROCm/FlyDSL

New pull request New
36 Open 545 Closed
36 Open 545 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

Add SUPPORTED_ARCHS table and is_arch_supported() helper
#678 opened Jun 12, 2026 by xudoyuan Collaborator • Draft
1 task
[Chore] Remove unreachable legacy expr/rocdl.py
#677 opened Jun 12, 2026 by sjfeng1999 Collaborator Loading…
1 task
1
CI: update FlyDSL vLLM runner
#676 opened Jun 11, 2026 by gyohuangxin Member Loading…
1
ci: add CI performance dashboard at /ci-dashboard
#675 opened Jun 11, 2026 by jhinpan Contributor Loading…
21
[Perf] flash_attn gfx950: dwordx4 O stores + flash-decoding split-K
#670 opened Jun 10, 2026 by jhinpan Contributor • Draft
perf(jit): lean cache-key fast path for @flyc.jit launches
#669 opened Jun 9, 2026 by fsx950223 Contributor Loading…
5
scripts: add HIP->FlyDSL multi-agent port orchestrator
#666 opened Jun 8, 2026 by fsx950223 Contributor Loading…
6
perf(rmsnorm): vectorize generic path and simplify block reduction
#662 opened Jun 6, 2026 by kudomcho Loading…
1
enh(hotspot_analyzer): add --kernel filter for CSV metadata matching
#657 opened Jun 4, 2026 by Arist12 Contributor Loading…
enh(test_common): add profiler-safe HIP-event timing path to run_perftest
#656 opened Jun 4, 2026 by Arist12 Contributor Loading…
[gfx1250][gemm] Add PTPC FP8/A8W4, non-tile-aligned M, and strided A/C support
#649 opened Jun 3, 2026 by aoli26 Contributor Loading…
1 task done
4
Add layout algebra inference diagnostics
#648 opened Jun 3, 2026 by jhinpan Contributor • Draft
[Bugfix] rmsnorm: annotate known_block_size on large-M small-N path
#639 opened Jun 3, 2026 by jhinpan Contributor Loading…
1
3
[Feat] Complete BasisAttr support in IntTupleBuilder (#574)
#638 opened Jun 3, 2026 by jhinpan Contributor Loading…
1
3
Fix stale JIT dependency caches
#637 opened Jun 3, 2026 by jhinpan Contributor Loading…
1
4
feat(compiler): Add custom LLVM pass pipeline and plugin support to JIT
#613 opened Jun 2, 2026 by fsx950223 Contributor • Draft
3
Optimize rmsnorm/layernorm to get better performance than aiter/triton
#610 opened Jun 2, 2026 by cschenjunlin Contributor Loading…
[Feat] Add OCP-spec even_round E8M0 helper f32_to_e8m0_even
#590 opened May 28, 2026 by amd-satre • Draft
1 task done
[LLVM] Bump to llvm/llvm-project@87717bf9f81f
#575 opened May 27, 2026 by jli-melchior Contributor Loading…
Auto-discover MLIR ROCm toolkit from rocm-sdk Python wheels
#568 opened May 26, 2026 by mgehre-amd Contributor • Draft
4 of 6 tasks
[Enh] Improve type closure for primitive func
#552 opened May 21, 2026 by sjfeng1999 Collaborator Loading…
1 task
21
fix: backport manylinux_2_28 wheel build to v0.1.4 (post1 release)
#528 opened May 15, 2026 by kiran-thumma Collaborator • Draft
5 tasks
1
[Optimization]: Replace 'scf.if' with 'arith.select' for visit_ifExp
#512 opened May 12, 2026 by xudoyuan Collaborator • Draft
1 task
blockscale code gfx1250 (WIP)
#487 opened May 8, 2026 by omuhamma • Draft
1 task
@omuhamma
add gfx950 16x16x64 I8 MFMA support to MoE 2-stage GEMM
#461 opened Apr 30, 2026 by yadaish Collaborator • Draft
1 task
ProTip! Filter pull requests by the default branch with base:main.