Georgi GerganovandThiago Padilha e7ae4d718e metal: implement DeepSeek V4 hyper-connections (llama/26459) ...

- Implement GGML_OP_DSV4_HC_COMB, GGML_OP_DSV4_HC_PRE, and
  GGML_OP_DSV4_HC_POST with SIMDgroup register and shuffle optimized kernels.
- Add Metal dispatch and support plumbing and test the production Sinkhorn
  iteration count and embedding width.

Assisted-by: Codex

Co-authored-by: Thiago Padilha <thiago@padilha.cc>

2026-08-04 13:37:47 +03:00

..

cmake

ggml : Parallelize quant LUT init (llama/23595)

2026-05-25 12:26:07 +03:00

include

sync : ggml (#3962)

2026-07-31 09:11:28 +02:00

src

metal: implement DeepSeek V4 hyper-connections (llama/26459)

2026-08-04 13:37:47 +03:00

.gitignore

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

CMakeLists.txt

sync : ggml (#3962)

2026-07-31 09:11:28 +02:00