-
Notifications
You must be signed in to change notification settings - Fork 151
Pull requests: ByteDance-Seed/Triton-distributed
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
add fused EP all-to-all mega kernels(forward) for AMD GPUs
#175
opened Jun 2, 2026 by
WhatGhost
Loading…
Update AMD build doc AND Make rocshmem device-bitcode arch configurable
#174
opened May 28, 2026 by
WhatGhost
Loading…
2 tasks done
[METAX] feat: Update metax backend to triton3.6 version
#173
opened May 27, 2026 by
hufarmer
Contributor
Loading…
fix bugs when device is None in get_full_tflops_approx and add b200 tflops
#172
opened May 27, 2026 by
WhatGhost
Loading…
Modify ep_moe_fused 's backward to run with ep_size < 8
#171
opened May 26, 2026 by
WhatGhost
Loading…
Add cuBLAS+NCCL fast path for small GEMM in GEMM+ReduceScatter
#166
opened Apr 13, 2026 by
yxs
Loading…
Port the low latency allgather kernels to AMD
#162
opened Feb 25, 2026 by
erieaton-amd
Collaborator
•
Draft
ProTip!
Filter pull requests by the default branch with base:main.