Search results

[Perf Regression] 32 config(s) regressed @ 6619cc7d

performance

regression

Status: Open.

#830 In ROCm/ATOM;

· github-actions opened on May 19, 2026

[Perf Regression] 1 config(s) regressed @ 55245f46

performance

regression

Status: Open.

#828 In ROCm/ATOM;

· github-actions opened on May 18, 2026

[Perf Regression] 1 config(s) regressed @ 51349cfd

performance

regression

Status: Open.

#826 In ROCm/ATOM;

· github-actions opened on May 18, 2026

[Perf Regression] 7 config(s) regressed @ fdf23b9e

performance

regression

Status: Open.

#825 In ROCm/ATOM;

· github-actions opened on May 18, 2026

[Kernel Gap Analysis] DeepSeek-V4 AMD Porting — Block-by-Block Kernel Inventory

documentationImprovements or additions to documentationImprovements or additions to documentation

enhancementNew feature or requestNew feature or request

workstream

Status: Open.

#807 In ROCm/ATOM;

· ChuanLi1101 opened on May 15, 2026

Fail to run DeepSeek V3.2 on MI 300x

Status: Open.

#797 In ROCm/ATOM;

· LoadingZhang opened on May 15, 2026

[ATOM-Plugin][Attention] Refactor ATOM-Plugin Attention Architecture

Status: Open.

#758 In ROCm/ATOM;

· zejunchen-zejun opened on May 12, 2026

[Issue]: Qwen3NextMTPModel", "Qwen3_5MTPModel doesn't work with prefix caching

Status: Open.

#757 In ROCm/ATOM;

· functionstackx opened on May 12, 2026

[Bug]: Qwen3.5-35B-A3B / 27B BF16 accuracy regression at TP4 / TP8

ATOMAdded to frameworks-internal ATOM GitHub boardAdded to frameworks-internal ATOM GitHub board

bugSomething isn't workingSomething isn't working

regression

Status: Open.

Bug

#719 In ROCm/ATOM;

· zufayu opened on May 8, 2026

[RFC]: Enable ATOM as vLLM-Omni's out-of-tree Plugin

Status: Open.

#716 In ROCm/ATOM;

· Phi-C opened on May 8, 2026

[Tracker]: DeepSeek-V4 Support and Optimization on ATOM

workstream

Status: Open.

#707 In ROCm/ATOM;

· jamestangg opened on May 7, 2026

[Issue]: aiter ASM paged-attention with block_size=16

Status: Open.

#702 In ROCm/ATOM;

· yhl-amd opened on May 6, 2026