 Georgi Gerganov
|
0f2411f154
ggml : fix compile warnings (unused vars) (#4966)
|
1 year ago |
 snadampal
|
a07d0fee1f
ggml : add mmla kernels for quantized GEMM (#4966)
|
1 year ago |
 Johannes Gäßler
|
e4640d8fdf
lookup: add print for drafting performance (#5450)
|
1 year ago |
 Xuan Son Nguyen
|
907e08c110
server : add llama2 chat template (#5425)
|
1 year ago |
 Ian Bull
|
f026f8120f
metal : use autoreleasepool to avoid memory leaks (#5437)
|
1 year ago |
|
Georgi Gerganov
|
cd9aea63b5
scripts : update sync scripts with new backends
|
1 year ago |
|
Georgi Gerganov
|
43b65f5eb8
sync : ggml
|
1 year ago |
 Michael Podvitskiy
|
4633d93af0
ggml : add abort_callback for cpu backend (ggml/725)
|
1 year ago |
 Neuman Vong
|
4b7b38bef5
vulkan: Set limit for task concurrency (#5427)
|
1 year ago |
 Daniel Bevenius
|
e00d2a62dd
llava : add requirements.txt and update README.md (#5428)
|
1 year ago |
 Riley Stewart
|
7c777fcd5d
server : fix prompt caching for repeated prompts (#5420)
|
1 year ago |
 Paul Tsochantaris
|
e5ca3937c6
llama : do not cap thread count when MoE on CPU (#5419)
|
1 year ago |
 Marko Tasic
|
e4124c2477
readme : add JavaScript/Wasm repo (#5415)
|
1 year ago |
|
Michael Podvitskiy
|
b2f87cb64d
ggml : fix `error C2078: too many initializers` for MSVC ARM64 (#5404)
|
1 year ago |
 0cc4m
|
44fbe34360
Fix Vulkan crash on APUs with very little device memory (#5424)
|
1 year ago |
|
Johannes Gäßler
|
8e6a9d2de0
CUDA: more warps for mmvq on NVIDIA (#5394)
|
1 year ago |
 slaren
|
41f308f58e
llama : do not print "offloading layers" message in CPU-only builds (#5416)
|
1 year ago |
 Abhilash Majumder
|
6e99f2a04f
Fix f16_sycl cpy call from Arc (#5411)
|
1 year ago |
|
Daniel Bevenius
|
ff4ff05c5f
llava : add missing .py, and fix paths in README.md (#5414)
|
1 year ago |
|
Johannes Gäßler
|
b7b74cef36
fix trailing whitespace (#5407)
|
1 year ago |
 runfuture
|
4aa43fab56
llama : fix MiniCPM (#5392)
|
1 year ago |
|
Daniel Bevenius
|
a6e514a85f
llava: fix typo/formatting in README.md (#5405)
|
1 year ago |
|
Johannes Gäßler
|
26d4efd11e
sampling: fix top_k <= 0 (#5388)
|
1 year ago |
|
Georgi Gerganov
|
8504d2d0da
tests : .gitignore obj files
|
1 year ago |
|
Michael Podvitskiy
|
c4fbb6717c
CMAKE_OSX_ARCHITECTURES for MacOS cross compilation (#5393)
|
1 year ago |
 Ebey Abraham
|
8c933b70c2
fix typo in readme (#5399)
|
1 year ago |
 Kamil Tomšík
|
b906596bb7
Add Ava in the list of llama.cpp UIs (#4362)
|
1 year ago |
|
Johannes Gäßler
|
aa7ab99be2
CUDA: fixed mmvq kernel for bs 2,3,4 and -sm row (#5386)
|
1 year ago |
 Neo Zhang Jianyu
|
10afa6f1d1
[SYCL] update install make by w64devkit (#5297)
|
1 year ago |
 Xiao-Yong Jin
|
0ef46da632
llava-cli : always tokenize special tokens (#5382)
|
1 year ago |
