Skip to content

Pull requests: ROCm/FlyDSL

New pull request New
44 Open 654 Closed
44 Open 654 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

[Enh] Add rocdl.buffer_rsrc utilities: make_buffer_ptr & get_buffer_rsrc
#841 opened Jul 13, 2026 by sjfeng1999 Collaborator Loading…
1 task
8
[kernels]: add common/mem_ops for shared memory/atomic helpers
#839 opened Jul 13, 2026 by Phil-amd Member Loading…
Add a8w4 kernel for Quark mix-precision
#837 opened Jul 12, 2026 by amd-xiaoyu12 Loading…
1 task
[Misc] Propagate signatures through expr decorators
#835 opened Jul 12, 2026 by simondanielsson Loading…
1 task done
1
1
Gfx1250 tdm gather scatter
#833 opened Jul 12, 2026 by coderfeli Collaborator Loading…
1 task
1
[Feature] Extract reusable event-based benchmarking helper
#829 opened Jul 10, 2026 by jhinpan Collaborator • Draft
6 of 7 tasks
perf(pa tile): readable tile-programming PA decode kernel, matches/beats production
#825 opened Jul 10, 2026 by fsx950223 Contributor Loading…
2 tasks done
5
[MoE] Add gelu_tanh activation to MoE stage1 GEMM kernels
#823 opened Jul 9, 2026 by jonahbernard Loading…
1 task done
2
[Kernel] conv3d: parameterize tile size + add autotuner
#820 opened Jul 8, 2026 by jiacao-amd Contributor • Draft
2 tasks
[kernels] Migrate pa_decode_swa reduce kernel to SharedAllocator smem multi-gpu
#812 opened Jul 7, 2026 by xudoyuan Collaborator • Draft
1 task
1
[layernorm] Add backward pass for training (PR 3/3, #769)
#801 opened Jul 3, 2026 by jhinpan Collaborator Loading…
4
[4/5] autotune: CI guard + committed-config regression check (#770)
#788 opened Jul 1, 2026 by jhinpan Collaborator Loading…
5
[3/5] autotune: offline config emit + runtime lookup (#770)
#786 opened Jul 1, 2026 by jhinpan Collaborator Loading…
8
[2/5] autotune: two-track config + first real adopter (rmsnorm) (#770)
#785 opened Jul 1, 2026 by jhinpan Collaborator Loading…
26
flash_attn_generic: replace raw arith.* FP ops with FlyDSL-typed fast…
#764 opened Jun 29, 2026 by xudoyuan Collaborator • Draft
1 task
1
5
[repro] flash_attn_generic: concise causal-mask loop trips dynamic-if…
#763 opened Jun 29, 2026 by xudoyuan Collaborator • Draft
1 task
FlyDSL gemm_decode: small-M dense GEMM kernels (BF16/FP8/blockscale)
#757 opened Jun 26, 2026 by vedenev-amd • Draft
1 task
@vedenev-amd
1
runtime: hard-fail mgpuModuleLoadJIT on HIP
#748 opened Jun 25, 2026 by fallintoplace Loading…
2
fix tile syntax in divide
#746 opened Jun 25, 2026 by tingqli Contributor Loading…
1 task
3
[Fix] Set identity block scales for CDNA4 MFMA_Scale in fp8 row-scale…
#744 opened Jun 25, 2026 by amd-songpiao Loading…
1
MXFP4 MoE tuning harness: legality filter, measurement, ledger + validated baseline (#708)
#736 opened Jun 25, 2026 by jhinpan Collaborator • Draft
1
[Kernel] feat: Add MXFP6-E2M3 activation support to mixed_moe_gemm_2stage
#709 opened Jun 19, 2026 by amd-satre Contributor Loading…
1 task done
1
Add SUPPORTED_ARCHS table and is_arch_supported() helper
#678 opened Jun 12, 2026 by xudoyuan Collaborator • Draft
1 task
perf(jit): lean cache-key fast path for @flyc.jit launches
#669 opened Jun 9, 2026 by fsx950223 Contributor Loading…
5
perf(rmsnorm): vectorize generic path and simplify block reduction
#662 opened Jun 6, 2026 by kudomcho Loading…
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.