[XPU] Add W8A8 FP8 linear kernel with multi-granularity quant support (#43645)

Signed-off-by: Chaojun,Zhang <chaojun.zhang@intel.com>
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Chaojun Zhang
2026-07-04 18:10:01 +08:00
committed by GitHub
co-authored by Copilot
parent e7c9df9449
commit 1a308c449c
6 changed files with 188 additions and 12 deletions
+6 -1
View File
@@ -156,6 +156,8 @@ LinearBackend = Literal[
"conch",
"exllama",
"emulation",
"xpu",
"xpu_woq",
]
@@ -217,7 +219,10 @@ class KernelConfig:
- "fbgemm": Use FBGEMM kernels
- "conch": Use Conch mixed-precision kernels
- "exllama": Use Exllama mixed-precision kernels
- "emulation": Use slow dequant-to-BF16 emulation (for testing only)"""
- "emulation": Use slow dequant-to-BF16 emulation (for testing only)
- "xpu": Use XPU kernels
- "xpu_woq": Use XPU kernels for weight-only quantization (e.g. W8A16)
"""
@field_validator("moe_backend", mode="before")
@classmethod