|
095e45100b
|
[AMD] [GLM-5.3-Flash Day 0] Route mHC through AITER on gfx950 (#38545)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
Co-authored-by: Kevin Mi <45493463+kevin-mii@users.noreply.github.com>
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-21 22:24:29 -07:00 |
|
|
|
e1daf68304
|
[AMD] [GLM-5.3-Flash Day 0] Honor fused and per-expert names in quark exclude (#39317)
Co-authored-by: Yikai Zhang <ykzhang12@gmail.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
Co-authored-by: Kevin Mi <45493463+kevin-mii@users.noreply.github.com>
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-21 21:26:42 -07:00 |
|
|
|
b44e248682
|
[AMD] [GLM-5.3-Flash Day 0] Enable FP8 and Quark MXFP4 MoE on gfx950 (#38546)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
Co-authored-by: andyluo7 <andy.luo@amd.com>
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-21 21:07:37 -07:00 |
|
|
Raiden MakotoandRaiden-Makoto
|
4c0e85524d
|
[AMD] [GLM5] Enable dense-MHA short-context prefill fallback on gfx950 (#30808)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
|
2026-08-15 19:30:14 -07:00 |
|
|
Raiden MakotoandRaiden-Makoto
|
81d3c3ce77
|
[AMD] [GLM5] Guard cuda_runtime.h for ROCm in fused_metadata_copy (#29373)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
|
2026-06-26 23:29:19 -07:00 |
|
|
Raiden MakotoandRaiden-Makoto
|
7f376644e0
|
[AMD] [GLM5] Mark EAGLE verified on MI300X/MI325X (gfx942) in GLM-5.1 cookbook (#29313)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
|
2026-06-26 10:49:58 +08:00 |
|
|
Raiden MakotoandRaiden-Makoto
|
0075c8f02b
|
[AMD] [GLM5] GLM-5.1 MXFP4 (MI355X) + enable EAGLE for gfx950 in cookbook (#29194)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
|
2026-06-25 03:54:48 -07:00 |
|
|
Raiden MakotoandRaiden-Makoto
|
9215da2515
|
[AMD] [GLM5] skip redundant -inf pre-fill of HIP indexer MQA-logits (#28757)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
|
2026-06-24 23:21:39 -07:00 |
|
|
Raiden MakotoandRaiden-Makoto
|
7454735be9
|
[AMD] [GLM5] Add opt-in Triton fp8 sparse-MLA prefill kernel for gfx950 (#28975)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
|
2026-06-23 18:04:07 -07:00 |
|
|
Raiden MakotoandRaiden-Makoto
|
5e6d7c1615
|
[AMD] Fix DeepSeek-V4 fp8 KV path on gfx942 (e4m3fnuz) (#28455)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
|
2026-06-23 17:45:13 -07:00 |
|