Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

metal: implement DeepSeek V4 hyper-connections (#26459)

Browse Source 
- 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>
This commit is contained in:
Georgi Gerganov
2026-08-02 21:06:02 +03:00
committed by GitHub
co-authored by Thiago Padilha
parent bb4e0e1b3f
commit fffbcbdb9d
8 changed files with 397 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-ops.h
+1
View File
@@ -54,6 +54,7 @@ int ggml_metal_op_cumsum (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_get_rows (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_set_rows (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_diag (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_dsv4_hc (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_soft_max (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_ssm_conv (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_ssm_scan (ggml_metal_op_t ctx, int idx);