llama.cpp
[SYCL] Fix batched impl for NVidia GPU
#6164
Merged

[SYCL] Fix batched impl for NVidia GPU #6164

AidanBeltonS
AidanBeltonS
OuadiElfarouki
OuadiElfarouki approved these changes on 2024-03-19
NeoZhangJianyu
NeoZhangJianyu
AidanBeltonS
NeoZhangJianyu
NeoZhangJianyu
slaren
NeoZhangJianyu
abhilash1910
NeoZhangJianyu
Fix batched impl
10aef368
Maintain previous behaviour for igpu
d1cb8fed
AidanBeltonS AidanBeltonS force pushed from 421da299 to d1cb8fed 1 year ago
AidanBeltonS
AidanBeltonS
abhilash1910
abhilash1910 commented on 2024-03-21
abhilash1910
abhilash1910 commented on 2024-03-21
abhilash1910
abhilash1910 approved these changes on 2024-03-27
abhilash1910
abhilash1910 retrigger CI
cec6481a
abhilash1910 abhilash1910 requested a review from ggerganov ggerganov 1 year ago
ggerganov
ggerganov approved these changes on 2024-03-27
abhilash1910 abhilash1910 merged e82f9e2b into master 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone