[V1] [Hybrid] Mamba1 Automatic Prefix Caching (#26377)
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
This commit is contained in:
@@ -611,7 +611,11 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
|
||||
"Tensor? cache_indices,"
|
||||
"Tensor? has_initial_state,"
|
||||
"Tensor! ssm_states,"
|
||||
"int pad_slot_id) -> ()");
|
||||
"int pad_slot_id,"
|
||||
"int block_size,"
|
||||
"Tensor? block_idx_first_scheduled_token,"
|
||||
"Tensor? block_idx_last_scheduled_token,"
|
||||
"Tensor? initial_state_idx) -> ()");
|
||||
ops.impl("selective_scan_fwd", torch::kCUDA, &selective_scan_fwd);
|
||||
|
||||
// Hadamard transforms
|
||||
|
||||
Reference in New Issue
Block a user