Skip to content

Commit

Permalink
Revert "llama : simplify Mamba with advanced batch splits (ggerganov#…
Browse files Browse the repository at this point in the history
…8526)"

This reverts commit a1631e5.
  • Loading branch information
Nexesenex committed Aug 27, 2024
1 parent 5078aa8 commit 2b41d79
Show file tree
Hide file tree
Showing 4 changed files with 678 additions and 1,137 deletions.
9 changes: 6 additions & 3 deletions ggml/include/ggml.h
Original file line number Diff line number Diff line change
Expand Up @@ -1778,8 +1778,10 @@ extern "C" {

GGML_API struct ggml_tensor * ggml_ssm_conv(
struct ggml_context * ctx,
struct ggml_tensor * sx,
struct ggml_tensor * c);
struct ggml_tensor * s,
struct ggml_tensor * x,
struct ggml_tensor * c,
struct ggml_tensor * sq);

GGML_API struct ggml_tensor * ggml_ssm_scan(
struct ggml_context * ctx,
Expand All @@ -1788,7 +1790,8 @@ extern "C" {
struct ggml_tensor * dt,
struct ggml_tensor * A,
struct ggml_tensor * B,
struct ggml_tensor * C);
struct ggml_tensor * C,
struct ggml_tensor * sq);

// partition into non-overlapping windows with padding if needed
// example:
Expand Down
Loading

0 comments on commit 2b41d79

Please sign in to comment.