 Daniel Bevenius
|
01aae2b497
baby-llama : remove duplicate vector include
|
hai 1 ano |
 Georgi Gerganov
|
4b77ea95f5
flake.lock: Update (#8847)
|
hai 1 ano |
 jdomke
|
76614f352e
ggml : reading the runtime sve config of the cpu (#8709)
|
hai 1 ano |
 Sigbjørn Skjæret
|
b72c20b85c
Fix conversion of unnormalized BF16->BF16 weights (#7843)
|
hai 1 ano |
 Mengqing Cao
|
e09a800f9a
cann: Fix ggml_cann_im2col for 1D im2col (#8819)
|
hai 1 ano |
 Ouadie EL FAROUKI
|
0fbbd88458
[SYCL] Fixing wrong VDR iq4nl value (#8812)
|
hai 1 ano |
 matteo
|
afbb4c1322
ggml-cuda: Adding support for unified memory (#8035)
|
hai 1 ano |
 Alex O'Connell
|
b7a08fd5e0
Build: Only include execinfo.h on linux systems that support it (#8783)
|
hai 1 ano |
 slaren
|
7a11eb3a26
cuda : fix dmmv cols requirement to 2*GGML_CUDA_DMMV_X (#8800)
|
hai 1 ano |
 wangshuai09
|
c8a0090922
cann: support q8_0 for Ascend backend (#8805)
|
hai 1 ano |
 Igor Okulist
|
afbbcf3c04
server : update llama-server embedding flag documentation (#8779)
|
hai 1 ano |
 Clint Herron
|
ed9d2854c9
Build: Fix potential race condition (#8781)
|
hai 1 ano |
 pculliton
|
398ede5efe
Adding Gemma 2 2B configs (#8784)
|
hai 1 ano |
 Borislav Stanimirov
|
44d28ddd5c
cmake : fix use of external ggml (#8787)
|
hai 1 ano |
 Someone
|
268c566006
nix: cuda: rely on propagatedBuildInputs (#8772)
|
hai 1 ano |
 Brian
|
7e72aa74fd
py: add_array() will not add to kv store if value is an empty array (#8774)
|
hai 1 ano |
 l3utterfly
|
7c27a19b2e
added android implementation of ggml_print_backtrace_symbols (#8751)
|
hai 1 ano |
|
Georgi Gerganov
|
140074bb86
flake.lock: Update (#8729)
|
hai 1 ano |
|
wangshuai09
|
6e2b6000e5
cann: update cmake (#8765)
|
hai 1 ano |
 zhentaoyu
|
c887d8b017
[SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707)
|
hai 1 ano |
 CarterLi999
|
75af08c475
ggml: bugfix: fix the inactive elements is agnostic for risc-v vector (#8748)
|
hai 1 ano |
 R0CKSTAR
|
439b3fc75a
cuda : organize vendor-specific headers into vendors directory (#8746)
|
hai 1 ano |
 Meng, Hengyu
|
0832de7236
[SYCL] add conv support (#8688)
|
hai 1 ano |
 Johannes Gäßler
|
6eeaeba126
cmake: use 1 more thread for non-ggml in CI (#8740)
|
hai 1 ano |
 Austin
|
4730faca61
chore : Fix vulkan related compiler warnings, add help text, improve CLI options (#8477)
|
hai 1 ano |
 compilade
|
4c676c85e5
llama : refactor session file management (#8699)
|
hai 1 ano |
 R0CKSTAR
|
e54c35e4fb
feat: Support Moore Threads GPU (#8383)
|
hai 1 ano |
|
Georgi Gerganov
|
5e2727fe03
scripts : sync vulkan-shaders (#0)
|
hai 1 ano |
|
Georgi Gerganov
|
56f20aa25d
scripts : sync ggml-aarch64 sources
|
hai 1 ano |
|
Georgi Gerganov
|
345c8c0c87
ggml : add missing semicolon (#0)
|
hai 1 ano |
