vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)

Browse source 
* 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:
Zhiyuan Li 2024-11-07 18:19:10 +11:00 • committed by GitHub
parent 5c333e0140
commit 3bcd40b3c5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 1977 additions and 1027 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ggml/src/ggml-cuda.cu
View file

@ -36,7 +36,7 @@
#include "ggml-cuda/tsembd.cuh"
#include "ggml-cuda/unary.cuh"
#include "ggml-cuda/upscale.cuh"
#include "ggml-cuda/rwkv-wkv.cuh"
#include "ggml-cuda/wkv6.cuh"
#include <algorithm>
#include <array>
@ -2319,8 +2319,8 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
case GGML_OP_CROSS_ENTROPY_LOSS:
ggml_cuda_cross_entropy_loss(ctx, dst);
break;
case GGML_OP_RWKV_WKV:
ggml_cuda_op_rwkv_wkv(ctx, dst);
case GGML_OP_RWKV_WKV6:
ggml_cuda_op_rwkv_wkv6(ctx, dst);
break;
case GGML_OP_CROSS_ENTROPY_LOSS_BACK:
ggml_cuda_cross_entropy_loss_back(ctx, dst);
@ -3153,7 +3153,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_OP_ARANGE:
case GGML_OP_TIMESTEP_EMBEDDING:
case GGML_OP_LEAKY_RELU:
case GGML_OP_RWKV_WKV:
case GGML_OP_RWKV_WKV6:
return true;
case GGML_OP_FLASH_ATTN_EXT: {
#ifndef FLASH_ATTN_AVAILABLE