Skip to content

Pull requests: ROCm/aiter

New pull request New
185 Open 1,904 Closed
185 Open 1,904 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

support naive mrope in get_rope ci:all
#2292 opened Mar 16, 2026 by ganyi1996ppo Loading…
1 task
4
Add tuned csv files for Gemm and MoE to accelerate Kimi-K2
#2290 opened Mar 16, 2026 by wuhuikx Loading…
2
Feat gen kv prefix preshuffle1
#2288 opened Mar 16, 2026 by jiayyu Loading…
1 task
6
Add 32x128 and 64x128 asm kernels to support qwen3-next TP4 ci:atom
#2285 opened Mar 15, 2026 by JohnNikolay84 Loading…
@JohnNikolay84
1
Use arch-aware fp8 dtype in tests for gfx1250 support
#2284 opened Mar 15, 2026 by sunway513 Loading…
3 of 4 tasks
8
Store swa kv for sglang ci:all
#2283 opened Mar 15, 2026 by kkHuang-amd Loading…
1 task done
Add gfx1250 support: GFX_MAP + default GEMM/MHA configs
#2282 opened Mar 15, 2026 by sunway513 Loading…
3 of 5 tasks
3
[Triton MoE] Add optimized Gluon kernel for AMD CDNA3 with K-dimension unrolling
#2277 opened Mar 14, 2026 by jwu10003 Loading…
1 task done
[Triton] Enable fp8 bwd test
#2276 opened Mar 14, 2026 by micmelesse Loading…
1 task
14
Gluon gfx12 a8w8blockscale v1 to main
#2275 opened Mar 13, 2026 by amirumoAMD • Draft
1 task
19
[TRITON] Add Attention support to the bench_models benchmarking script ci:all enhancement New feature or request triton
#2274 opened Mar 13, 2026 by lucas-santos-amd Loading…
1 task
@lucas-santos-amd
2
replace ck_tile type covert by opus cast
#2271 opened Mar 13, 2026 by yzhou103 • Draft
1 task
8
Add topk implementations: csdn baseline, csdn reduceAtomic, carlus ba…
#2270 opened Mar 13, 2026 by chuanbowang2026 Loading…
2 tasks
CI: Switch Triton tests from MI325 to MI355 runners
#2269 opened Mar 13, 2026 by gyohuangxin Loading…
2 tasks
3
[TRITON] Unified attention FP8 cleanup
#2267 opened Mar 13, 2026 by cagrikymk • Draft
1 of 2 tasks
3
optimize the fa fwd and bwd kernels
#2265 opened Mar 12, 2026 by scxiao Loading…
1 task done
3
[CI] Flash Attention CK CI
#2264 opened Mar 12, 2026 by micmelesse • Draft
1 task
1
Introduce asm fmoe kernels that do not require bf16->fp8 quantization ci:atom ci:sglang ci:vllm
#2262 opened Mar 12, 2026 by JohnNikolay84 Loading…
1 task
@JohnNikolay84
3
Gemm & moe tunning for DeepSeek-R1 in InferenceX FP4 case
#2261 opened Mar 12, 2026 by inkcherry Loading…
1 task
4
[TRITON] Update config of MHA PE forward kernel on gfx950 ci:atom ci:sglang ci:vllm enhancement New feature or request triton
#2260 opened Mar 12, 2026 by brunomazzottiamd Loading…
1 task done
@brunomazzottiamd
5
Add performance parity tests for AITER kernels
#2258 opened Mar 12, 2026 by ChuanLi1101 Loading…
4 tasks
1
[FLYDSL] Add GDR decode kernels
#2257 opened Mar 12, 2026 by xytpai Loading…
1
refactor: use ctypes binding
#2255 opened Mar 12, 2026 by amd-ruitang3 Loading…
1 task
7
Capture git errors in case git doesn't exist
#2254 opened Mar 11, 2026 by t2h-fb Loading…
fix fmoe_int8_g1u0_a16
#2251 opened Mar 11, 2026 by junhaha666 Loading…
1 task
4
ProTip! Adding no:label will show everything without a label.