 Borislav Stanimirov
|
44d28ddd5c
cmake : fix use of external ggml (#8787)
|
1 year ago |
 Someone
|
268c566006
nix: cuda: rely on propagatedBuildInputs (#8772)
|
1 year ago |
 Brian
|
7e72aa74fd
py: add_array() will not add to kv store if value is an empty array (#8774)
|
1 year ago |
 l3utterfly
|
7c27a19b2e
added android implementation of ggml_print_backtrace_symbols (#8751)
|
1 year ago |
 Georgi Gerganov
|
140074bb86
flake.lock: Update (#8729)
|
1 year ago |
 wangshuai09
|
6e2b6000e5
cann: update cmake (#8765)
|
1 year ago |
 zhentaoyu
|
c887d8b017
[SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707)
|
1 year ago |
 CarterLi999
|
75af08c475
ggml: bugfix: fix the inactive elements is agnostic for risc-v vector (#8748)
|
1 year ago |
 R0CKSTAR
|
439b3fc75a
cuda : organize vendor-specific headers into vendors directory (#8746)
|
1 year ago |
 Meng, Hengyu
|
0832de7236
[SYCL] add conv support (#8688)
|
1 year ago |
 Johannes Gäßler
|
6eeaeba126
cmake: use 1 more thread for non-ggml in CI (#8740)
|
1 year ago |
 Austin
|
4730faca61
chore : Fix vulkan related compiler warnings, add help text, improve CLI options (#8477)
|
1 year ago |
 compilade
|
4c676c85e5
llama : refactor session file management (#8699)
|
1 year ago |
 R0CKSTAR
|
e54c35e4fb
feat: Support Moore Threads GPU (#8383)
|
1 year ago |
|
Georgi Gerganov
|
5e2727fe03
scripts : sync vulkan-shaders (#0)
|
1 year ago |
|
Georgi Gerganov
|
56f20aa25d
scripts : sync ggml-aarch64 sources
|
1 year ago |
|
Georgi Gerganov
|
345c8c0c87
ggml : add missing semicolon (#0)
|
1 year ago |
|
Georgi Gerganov
|
ae7985cd7b
sync : ggml
|
1 year ago |
 Mahesh Madhav
|
a05ca93697
ggml : loop tiling optimizations for scalar path (ggml/898)
|
1 year ago |
 Ivan Filipov
|
9f77d899b7
ggml: add support for float16 input tensors in pooling operations (ggml/895)
|
1 year ago |
 Tony Wasserka
|
203b7f1531
vulkan : initialize vk_buffer_struct members to VK_NULL_HANDLE (ggml/893)
|
1 year ago |
|
Borislav Stanimirov
|
d2b851bfa1
cmake : only enable GGML_NATIVE and x86 flags if not crosscompiling (ggml/885)
|
1 year ago |
 Daniel Bevenius
|
c12b6e8ee7
ggml : remove unnecessary UNUSED macro call (ggml/880)
|
1 year ago |
 Jeffrey Morgan
|
b5e95468b1
llama : add support for llama 3.1 rope scaling factors (#8676)
|
1 year ago |
|
Georgi Gerganov
|
92090eca21
llama : add function for model-based max number of graph nodes (#8622)
|
1 year ago |
|
Daniel Bevenius
|
9d03d085dd
common : add --no-warmup option for main/llama-cli (#8712)
|
1 year ago |
|
wangshuai09
|
bfb4c74981
cann: Fix Multi-NPU execution error (#8710)
|
1 year ago |
 slaren
|
2b1f616b20
ggml : reduce hash table reset cost (#8698)
|
1 year ago |
 Judd
|
01245f5b16
llama : fix order of parameters (#8706)
|
1 year ago |
 Yaiko
|
01aec4a631
server : add Speech Recognition & Synthesis to UI (#8679)
|
1 year ago |
