mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-06-20 23:55:04 +00:00
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (llama/10133)
* rwkv6: rename to wkv6 * rwkv6: support avx2 avx512 armv8 armv9 * rwkv6: update cuda file name * rwkv6: rename params * wkv on sycl * sycl: add some ops * sycl: Enhance OP support judgment * wkv6: drop armv9 and tranfer to GGML style ggml-ci * sync : ggml * update the function to use appropriate types * fix define error * Update ggml/src/ggml-cpu.c * add appropriate asserts * move element-wise functions outside * put the declaration outside the loop * rewrite to be more inline with the common pattern for distributing threads * use recommended way GGML_TENSOR_LOCALS --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Diego Devesa <slarengh@gmail.com> Co-authored-by: Plamen Minev <pacominev@gmail.com> Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com> Co-authored-by: Meng, Hengyu <airdldl@163.com>
This commit is contained in:
committed by
Georgi Gerganov
parent
31c3482a4e
commit
42398f13b0
@ -509,7 +509,7 @@ extern "C" {
|
||||
GGML_OP_WIN_UNPART,
|
||||
GGML_OP_GET_REL_POS,
|
||||
GGML_OP_ADD_REL_POS,
|
||||
GGML_OP_RWKV_WKV,
|
||||
GGML_OP_RWKV_WKV6,
|
||||
|
||||
GGML_OP_UNARY,
|
||||
|
||||
@ -1819,7 +1819,7 @@ extern "C" {
|
||||
struct ggml_tensor * pw,
|
||||
struct ggml_tensor * ph);
|
||||
|
||||
GGML_API struct ggml_tensor * ggml_rwkv_wkv(
|
||||
GGML_API struct ggml_tensor * ggml_rwkv_wkv6(
|
||||
struct ggml_context * ctx,
|
||||
struct ggml_tensor * k,
|
||||
struct ggml_tensor * v,
|
||||
|
Reference in New Issue
Block a user