-
Notifications
You must be signed in to change notification settings - Fork 75
Pull requests: nnstreamer/nntrainer
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Tensor] ShortTensor class with quantized signed 16-bit integer
Need Review
#2866
opened Jan 10, 2025 by
djeong20
Loading…
[GPU] Added multiple fp16 unittests for blas kernel operations.
Need Review
#2863
opened Jan 9, 2025 by
niket-agarwal
Loading…
[ Wait for #2858 ] [ Tensor ] Integrate saxpy and ele_add
Need Review
#2862
opened Jan 8, 2025 by
skykongkong8
Loading…
[Wait for #2848, #2856] [ Context ] Add Context Data Class
Need Review
#2860
opened Jan 7, 2025 by
jijoongmoon
Loading…
[OpenCL/GPU] Optimized Blas and Attention kernels with the latest GPU Pipeline.
Need Review
#2859
opened Jan 7, 2025 by
yashSingh0723
Loading…
[Tensor] Proposal for unifying tensor addition: remove add_i implementation
Need Review
#2858
opened Jan 7, 2025 by
djeong20
Loading…
[ neon ] Implement int8 mul neon simd kernel @open sesame 01/09 12:38
Need Review
#2857
opened Jan 7, 2025 by
skykongkong8
Loading…
[ Layer ] Move the Weight Read Function to Layer object
Need Review
#2856
opened Jan 7, 2025 by
jijoongmoon
Loading…
[GPU] Optimized operations in the blas kernels with the latest buffer changes.
PR/READY2MERGE
#2855
opened Jan 5, 2025 by
niket-agarwal
Loading…
[Wait for #2846][FSU] Modify Load Logic at FSU @open sesame 01/07 09:50
Need Review
#2854
opened Jan 3, 2025 by
DonghakPark
Loading…
[CharTensor] Enable QINT8 multiplication feature
Need Review
#2850
opened Dec 31, 2024 by
djeong20
Loading…
[Wait for #2849] [ Context ] Add Engine Class to manage Contexts
Need Review
rebase required
#2848
opened Dec 30, 2024 by
jijoongmoon
Loading…
[FSU] Modify the condition of LoadTensors
Need Review
#2846
opened Dec 27, 2024 by
SeoHyungjun
Loading…
[ Tensor ] Apply SIMD in matrix transpose fp32 @open sesame 12/18 10:16
PR/READY2MERGE
#2832
opened Dec 18, 2024 by
skykongkong8
Loading…
[GPU/OpenCL] Fused DotCL, Addition and RMS for optimization
#2831
opened Dec 17, 2024 by
yashSingh0723
•
Draft
[ GPU ] split kernel registration from forwarding function in
addition_layer_cl
and transpose_cl
PR/READY2MERGE
#2810
opened Nov 29, 2024 by
EunjuYang
Loading…
[ GPU ] split kernel register from forwarding function in
swiglu_cl
@open sesame 12/02 10:40
PR/READY2MERGE
#2809
opened Nov 29, 2024 by
EunjuYang
Loading…
[layer] add pow operation layer @open sesame 12/06 20:13
PR/READY2MERGE
#2801
opened Nov 20, 2024 by
baek2sm
Loading…
[Wait for #2727] [ GPU/OpenCL ] enable X86 Opencl with
ENABLE_FP16=false
Need Review
#2783
opened Nov 4, 2024 by
EunjuYang
Loading…
[ Tensor ] Refactor blas/math related files into cpu backend considering arch-dep @open sesame 10/02 13:19
Need Review
Refactor🏭
#2549
opened Apr 18, 2024 by
skykongkong8
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2025-01-09.