llama.cpp
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration
#10133
Merged
Overview
Commits
33
Changes
View On GitHub

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

airMeng merged 33 commits into ggml-org:master from zhiyuan1i:master
zhiyuan1i
github-actions github-actions added testing
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
zhiyuan1i zhiyuan1i force pushed from c6f4aefa to 7febf6e2 342 days ago
github-actions github-actions added SYCL
zhiyuan1i zhiyuan1i force pushed from f0158fa8 to 7febf6e2 342 days ago
zhiyuan1i
github-actions github-actions added documentation
zhiyuan1i zhiyuan1i changed the title Optimize RWKV6 Operator Naming and Implement Multi-core CPU Acceleration Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration 342 days ago
zhiyuan1i zhiyuan1i force pushed from 1643e280 to 2011ddad 342 days ago
zhiyuan1i rwkv6: rename to wkv6
f66c75a4
zhiyuan1i rwkv6: support avx2 avx512 armv8 armv9
b4254c55
zhiyuan1i rwkv6: update cuda file name
e198f7b9
zhiyuan1i rwkv6: rename params
3f75f121
zhiyuan1i wkv on sycl
2fc42b6a
zhiyuan1i sycl: add some ops
bee1cec7
zhiyuan1i sycl: Enhance OP support judgment
1c58096f
zhiyuan1i zhiyuan1i force pushed from 563153ae to 1c58096f 341 days ago
zhiyuan1i Merge branch 'ggerganov:master' into master
042c3e0f
zhiyuan1i wkv6: drop armv9 and tranfer to GGML style
811aa872
zhiyuan1i zhiyuan1i force pushed from e16e2f39 to 811aa872 341 days ago
ggerganov flake.lock: Update (#10146)
4d266310
ggerganov metal : minor fixup in FA kernel (#10143)
b1896308
slaren ggml : move CPU backend to a separate file (#10144)
89812b15
pminev metal : fix minor string leaks (ggml/1004)
8050d021
ykhrustalev cmake : make it possible linking ggml as external lib (ggml/1003)
eb5711c4
ggerganov sync : ggml
153251f7
zhiyuan1i Merge branch 'ggerganov:master' into master
5f792141
zhiyuan1i fix: update changes to upstream
61c665b7
zhiyuan1i
zhiyuan1i fix: add defualt
9ea34a78
ggerganov
ggerganov commented on 2024-11-04
zhiyuan1i Update ggml/src/ggml-sycl/outprod.cpp
8c7b4ec2
zhiyuan1i Update ggml/src/ggml-sycl/wkv6.cpp
bb0685fa
zhiyuan1i update the function to use appropriate types
81cb3012
zhiyuan1i zhiyuan1i requested a review from ggerganov ggerganov 340 days ago
zhiyuan1i fix define error
a878502f
ggerganov
ggerganov commented on 2024-11-04
zhiyuan1i Update ggml/src/ggml-cpu.c
b8160247
airMeng
airMeng approved these changes on 2024-11-04
zhiyuan1i add appropriate asserts
72e44325
zhiyuan1i move element-wise functions outside
35a1a2df
zhiyuan1i Update ggml/src/ggml-sycl/concat.cpp
6a1e977e
zhiyuan1i put the declaration outside the loop
a749ba77
zhiyuan1i rewrite to be more inline with the common pattern for distributing th…
4693b461
zhiyuan1i use recommended way GGML_TENSOR_LOCALS
4574795c
zhiyuan1i zhiyuan1i requested a review from ggerganov ggerganov 340 days ago
zhiyuan1i Merge branch 'ggerganov:master' into master
acb1b9d2
zhiyuan1i remove some codes
e264c35f
NeoZhangJianyu
NeoZhangJianyu approved these changes on 2024-11-05
zhiyuan1i update lint
623db3b0
zhiyuan1i Merge branch 'ggerganov:master' into master
98e070c1
ggerganov
ggerganov approved these changes on 2024-11-05
airMeng airMeng merged 3bcd40b3 into master 337 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
documentation testing Nvidia GPU ggml SYCL
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum