Add XPU MLA Sparse backend for DeepSeek v3.2 (#33230)

Signed-off-by: Zhang, Wuxun <wuxun.zhang@intel.com>
This commit is contained in:
Wuxun Zhang
2026-03-11 19:19:15 +08:00
committed by GitHub
parent 40c0461f24
commit e584dce52b
9 changed files with 940 additions and 24 deletions
+1
View File
@@ -214,3 +214,4 @@ configuration.
| `ROCM_AITER_MLA_SPARSE` | fp16, bf16 | `auto`, `bfloat16` | 1 | Any | ❌ | ✅ | ❌ | ❌ | Decoder | N/A |
| `ROCM_AITER_TRITON_MLA` | fp16, bf16 | `auto` | Any | Any | ❌ | ❌ | ❌ | ❌ | Decoder | N/A |
| `TRITON_MLA` | fp16, bf16 | `auto`, `bfloat16` | %16 | Any | ❌ | ❌ | ❌ | ✅ | Decoder | Any |
| `XPU_MLA_SPARSE` | fp16, bf16 | `auto`, `bfloat16` | Any | 576 | ❌ | ✅ | ❌ | ❌ | Decoder | Any |