Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
This project is mirrored from
https://github.com/ggerganov/llama.cpp
. Pull mirroring updated
Sep 19, 2024
.
b3516
064cdc26
·
vulkan : fix Qantized Mat-Vec Mul on AMD GPUs for ncols < 64 (#8855)
·
Aug 05, 2024
b3515
5587e57a
·
sync : ggml
·
Aug 05, 2024
b3512
c02b0a8a
·
cann: support q4_0 model (#8822)
·
Aug 05, 2024
b3510
978ba3d8
·
Server: Don't ignore llama.cpp params (#8754)
·
Aug 04, 2024
b3509
ecf6b7f2
·
batched-bench : handle empty `-npl` (#8839)
·
Aug 04, 2024
b3508
01aae2b4
·
baby-llama : remove duplicate vector include
·
Aug 04, 2024
b3506
76614f35
·
ggml : reading the runtime sve config of the cpu (#8709)
·
Aug 03, 2024
b3505
b72c20b8
·
Fix conversion of unnormalized BF16->BF16 weights (#7843)
·
Aug 02, 2024
b3504
e09a800f
·
cann: Fix ggml_cann_im2col for 1D im2col (#8819)
·
Aug 02, 2024
b3503
0fbbd884
·
[SYCL] Fixing wrong VDR iq4nl value (#8812)
·
Aug 02, 2024
b3502
afbb4c13
·
ggml-cuda: Adding support for unified memory (#8035)
·
Aug 01, 2024
b3501
b7a08fd5
·
Build: Only include execinfo.h on linux systems that support it (#8783)
·
Aug 01, 2024
b3500
7a11eb3a
·
cuda : fix dmmv cols requirement to 2*GGML_CUDA_DMMV_X (#8800)
·
Aug 01, 2024
b3499
c8a00909
·
cann: support q8_0 for Ascend backend (#8805)
·
Aug 01, 2024
b3498
afbbcf3c
·
server : update llama-server embedding flag documentation (#8779)
·
Jul 31, 2024
b3497
ed9d2854
·
Build: Fix potential race condition (#8781)
·
Jul 31, 2024
b3496
398ede5e
·
Adding Gemma 2 2B configs (#8784)
·
Jul 31, 2024
b3495
44d28ddd
·
cmake : fix use of external ggml (#8787)
·
Jul 31, 2024
b3490
6e2b6000
·
cann: update cmake (#8765)
·
Jul 30, 2024
b3489
c887d8b0
·
[SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707)
·
Jul 30, 2024
Prev
1
…
6
7
8
9
10
11
12
13
14
…
123
Next