Skip to content

Pull requests: ROCm/composable_kernel

New pull request New
48 Open 1,499 Closed
48 Open 1,499 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

[CK_TILE] Support moe with up gemm
#1793 opened Jan 4, 2025 by huaiguxu • Draft
5 of 6 tasks
1
[CK_TILE] Add GetName for GEMM kernels
#1791 opened Jan 3, 2025 by aledudek Loading…
6 tasks done
1
[CK_TILE] fmha fwd splitkv optimization for decode (seqlen_q=1)
#1789 opened Jan 3, 2025 by poyenc Loading…
4 tasks done
@poyenc
[CK_TILE] Sync fmha fwd splitkv minor optimizations
#1785 opened Jan 1, 2025 by poyenc Loading…
2 tasks done
@poyenc
[CK_TILE] Adjust kBlockSize of reduce example for better perf
#1779 opened Dec 27, 2024 by ClementLinCF Loading…
3 tasks
1
CK Tile GEMM Block and Block Method Selection with new 2x2 default policy warps layout
#1776 opened Dec 26, 2024 by ThomasNing Loading…
5 of 6 tasks
@ThomasNing
15
Dev/merge u8w8
#1774 opened Dec 24, 2024 by coderfeli Loading…
Grouped convolution backward weight special vector size loads
#1772 opened Dec 23, 2024 by bartekxk Loading…
6 tasks done
@bartekxk
[Draft] Revive QsKsVs FMHA pipeline
#1765 opened Dec 19, 2024 by tenpercent • Draft
1
fix: preprocessor directives logic error if/else
#1764 opened Dec 19, 2024 by deepsek Loading…
device_prop.hpp: move static map to helper function and initialize there
#1763 opened Dec 18, 2024 by coconutruben Loading…
3 of 6 tasks
1
CK-Tile Grouped GEMM refactor and post PR fixes
#1756 opened Dec 17, 2024 by mozga-amd Loading…
16
[Ck tile] Use raw store to improve layernorm performance
#1752 opened Dec 16, 2024 by rocking5566 Loading…
1
Ck tile/gemm perf measure
#1750 opened Dec 16, 2024 by ThomasNing Loading…
9
enable bias feature that add bias before adding residual (for rtpllm project)
#1741 opened Dec 11, 2024 by AMD-dteng Loading…
6
disable atomicAdd for C Output Vector Length = 1 with 16bit data type
#1737 opened Dec 10, 2024 by zjing14 Loading…
4
Add Grouped Convolution and GEMM documentation
#1719 opened Dec 5, 2024 by bartekxk Loading…
@bartekxk
11
[CK TILE] Support pure quantization
#1703 opened Nov 29, 2024 by rocking5566 Loading…
[BUGFix] Reorder GetSmemSize Related API
#1683 opened Nov 21, 2024 by LeiWang1999 Loading…
@LeiWang1999
1
add batched_transpose implement
#1660 opened Nov 13, 2024 by fangche123 • Draft
@ThomasNing
16
Apply universal gemm to bwd_weight_cshuffle operator
#1658 opened Nov 12, 2024 by mozga-amd Loading…
22
Update ck_a8w8
#1636 opened Nov 5, 2024 by aska-0096 Loading…
A prototype of TF32 gemm
#1632 opened Nov 4, 2024 by zjing14 • Draft
[do not review] int4 scale based on jzhang's pre work noCI Disable testing on supported CI systems: math libraries CI has this feature enabled..
#1628 opened Nov 4, 2024 by mtgu0705 • Draft
[DO NOT REVIEW] Add int4 dequant with scale only supports based on ZhangJing's PR #1572 noCI Disable testing on supported CI systems: math libraries CI has this feature enabled..
#1627 opened Nov 4, 2024 by mtgu0705 • Draft
ProTip! Add no:assignee to see everything that’s not assigned.