Nexesenex 0fdac83272 Fix Q8_0 graph reduce type ...

Analogous to the BF16 fix in eea6a82b25, this adds proper Q8_0
type handling in ggml_cuda_op_add:

- Add k_add_q8_0_f32 kernel: dequantize Q8_0, add F32, store F32
- Add k_add_q8_0_q8_0_f32 kernel: dequantize two Q8_0, add, store F32
- Add Q8_0+Q8_0/Q8_0+F32/F32+Q8_0 branches in the F32 dst (else) block,
  preventing Q8_0 data from falling through to the incorrect half cast
- Expand Q8_0 dst branch to handle F32+Q8_0->Q8_0 (swapped args), not
  just Q8_0+F32->Q8_0

2026-06-14 16:13:17 +02:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

MLA TP -khad: ggml_dequant_hadamard fused op + wv_b/wk_b_pp Hadamard fold (#1852)

2026-05-21 07:29:15 +03:00

src

Fix Q8_0 graph reduce type

2026-06-14 16:13:17 +02:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

ggml : default GGML_WIN_VER to 0x0A00 (Windows 10) (#1755)

2026-05-08 13:23:04 +03:00