14 Commits
Author SHA1 Message Date
Duyi-Wang 80e9a4ec74 [AMD] [Docker] Update MoRI to v1.2.3 (#38411) 2026-09-07 21:24:43 -07:00
Duyi-Wang 429ac2d82c [AMD] Fix DSv4 draft extend taking the target compression path during prefill (#37713) 2026-09-03 02:46:49 -07:00
Duyi-Wang 27a52d2530 [Docs] Tune DeepSeek-V4 HiCache for MI355X PD (#31452)
Signed-off-by: Duyi-Wang <duyi.wang@amd.com>
2026-07-17 11:50:58 +08:00
Duyi-Wang c9ceab34cf [AMD] [Docker] Update MoRI to v1.2.1 (#29394) 2026-07-05 19:37:04 -07:00
Duyi-Wang 63df86f5e7 [AMD] Skip eplb bookkeeping and topk remap when EPLB is not in use on mori-ep / HIP (#22985) (#28188) 2026-06-14 23:00:23 -07:00
Duyi-Wang ab7c4ab6bb [AMD] Fix correctness for AITER MLA backend with --page-size > 1 (#25556) 2026-06-02 23:01:19 -07:00
Duyi-Wang 8c190f6b91 [AMD] Add SGLANG_MORI_MOE_MAX_INPUT_TOKENS to truncate dispatch before MoE. (#22952) 2026-04-16 23:40:15 -07:00
Duyi-Wang ac593fed90 [AMD][Dockerfile] Support build-arg AITER_COMMIT for rocm.Dockerfile (#21949) 2026-04-03 01:54:28 -07:00
Duyi-Wang 61a902ce88 [AMD][MoRI] Auto-select dispatch quantization type from MoE weight dtype. (#21040) 2026-03-24 22:53:57 -07:00
Duyi-Wang 385a35bd11 [AMD][MORI] Fix MTP crash with FP4/FP8 dispatch and add NEXTN dispatch env vars. (#20647) 2026-03-17 01:13:42 -07:00
Duyi-Wang 8240a87306 [AMD] MORI-EP support for EP4. (#19578) 2026-02-28 13:13:46 -08:00
Duyi-Wang 98e433e305 [PD-Disagg][Fix] Remove 'test_external_dp_routing' from Rust Router constructor parameters. (#19492) 2026-02-27 02:40:01 -08:00
Duyi-Wang b0786cdf94 [AMD] Replace msgpack with msgspec in MORI-IO (#19007) 2026-02-19 23:04:15 -08:00
Duyi-WangandHAI 5ddc84e33e [AMD] MORI-EP inter kernel type switch (#18437)
Co-authored-by: HAI <hixiao@gmail.com>
2026-02-15 20:59:39 -08:00