Commit Graph
20 Commits
Author SHA1 Message Date
Zhaoyi Li b86a30afba [AMD][DI][CI] Add a SPUR cluster profile to AMD DI CI (#40113) 2026-09-21 01:56:46 -07:00
Zhaoyi Li 458987b5ac [AMD][MORI] Bump MoRI to 7c51d18 for ionic RoCE dmabuf fix (#509) (#37286) 2026-08-31 21:37:05 -07:00
Zhaoyi Liandjacky.cheng 24ab8f9ed9 [AMD] Qwen3.5: guard attn layers against empty DP-attention batch (#34474)
Co-authored-by: jacky.cheng <yichiche@amd.com>
2026-08-15 21:28:13 -07:00
Zhaoyi Li 9deb6952af [AMD][DI][CI] Add GLM-5.2 MXFP4 wide-EP16 2P1D nightly recipes (#34476) 2026-08-12 03:53:14 -07:00
Zhaoyi Li fc9479243e [AMD][DI][CI] 8/N Add GLM-5.2 MXFP4 1P1D DI/CI recipes (base + MTP + DP8/EP8) (#32120) 2026-08-06 22:56:40 -07:00
Zhaoyi Li b327d76682 [AMD] Bump mori to latest in sglang (#33462) 2026-08-04 15:12:40 -07:00
Zhaoyi LiandChen 48dcadc770 [AMD][DI][CI] 5/N Add DSV4 wide-EP16 4-node 2P1D nightly recipes (#31500)
Co-authored-by: Chen <bingxche@amd.com>
2026-08-03 22:08:00 -07:00
Zhaoyi Li a84e70eb1e [AMD][DI][CI] 6/N Add Kimi-K2.6 MXFP4 wide-EP16 2P1D nightly recipes (#33333) 2026-08-03 18:51:55 -07:00
Zhaoyi LiandChen 03f44c978a [AMD][DI][CI] Auto-mount latest host ionic/ibverbs userspace in the MI355X nightly launcher (fix ABI mismatch) (#33374)
Co-authored-by: Chen <bingxche@amd.com>
2026-08-03 18:14:14 -07:00
Zhaoyi LiandMichael 2c64b7782e [AMD][PD] Fix early-send cached-prefix KV racing the prefill forward on mori (#31368)
Co-authored-by: Michael <13900043+michaelzhang-ai@users.noreply.github.com>
2026-07-17 10:08:04 -07:00
Zhaoyi Liandbingxche 67361ff91b [AMD][DI][CI] 3/N Add Kimi K2.6 FP8 MI355X 1P1D nightly recipes (#29855)
Co-authored-by: bingxche <bingxche@amd.com>
2026-07-04 21:05:12 -07:00
Zhaoyi Li 0ab095eb3f [AMD]: hot-patch transformers dynamic_module_utils symlink bug (#29986) 2026-07-03 18:20:36 +08:00
Zhaoyi LiandMichael a3f6680874 [AMD]: docker(rocm) bump Mooncake to latest main + enable multi-protocol (#27730)
Co-authored-by: Michael <13900043+michaelzhang-ai@users.noreply.github.com>
2026-07-01 17:41:46 -07:00
Zhaoyi Liandbingxche 9bb7de9258 [AMD][DI][CI] 2/N Add DSV4 DP8/EP8 and MTP MI355X 1P1D nightly recipes (#29784)
Co-authored-by: bingxche <bingxche@amd.com>
2026-07-01 23:46:48 +08:00
Zhaoyi Liandbingxche 6bf15aa2b9 [AMD]: Enable NIXL PD disaggregation for ROCm(1/n) (#28348)
Co-authored-by: bingxche <bingxche@amd.com>
2026-06-29 21:23:09 -07:00
413aeac0c9 [AMD][DI][CI] 1/N: MI355X disaggregation nightly benchmark (#29084)
Co-authored-by: Michael <13900043+michaelzhang-ai@users.noreply.github.com>
Co-authored-by: bingxche <bingxche@amd.com>
Co-authored-by: yctseng0211 <yctseng@amd.com>
2026-06-25 19:21:28 -07:00
Zhaoyi Li 27a374eaef [AMD][CI] Use non-gated Qwen3-8B for MI35x disaggregation tests (#28678) 2026-06-18 14:29:35 -07:00
8e933e1914 AMD PD/D PR ci (#17183)
Co-authored-by: YC Tseng <yctseng@amd.com>
Co-authored-by: Bingxu Chen <bingxche@amd.com>
Co-authored-by: bingxche <Bingxu.Chen@amd.com>
2026-02-02 23:29:14 -08:00
Zhaoyi Li c555d794f7 Minor update for ROCm variable style (#5562) 2025-04-19 23:45:27 -07:00
Zhaoyi Li 3c9740d200 update variable naming and comments for rocm (#5299) 2025-04-11 23:15:05 -07:00