 Qingyou Meng
|
672dda10e4
ggml : fixed runtime bugs and compile errors related to GGML_PERF and GGML_DEBUG (#2219)
|
%!s(int64=2) %!d(string=hai) anos |
 Xiao-Yong Jin
|
6e7cca4047
llama : add custom RoPE (#2054)
|
%!s(int64=2) %!d(string=hai) anos |
 Evan Miller
|
e8035f141e
ggml : fix static_assert with older compilers #2024 (#2218)
|
%!s(int64=2) %!d(string=hai) anos |
 Georgi Gerganov
|
697966680b
ggml : sync (ggml_conv_2d, fix mul_mat bug, CUDA GLM rope)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
975221e954
ggml : broadcast mul_mat + conv batch support (#2199)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
4523d10d0c
ggml : add ggml_pool_1d and ggml_pool_2d
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
20d7740a9b
ggml : sync (abort callback, mul / add broadcast, fix alibi) (#2183)
|
%!s(int64=2) %!d(string=hai) anos |
 Spencer Sutton
|
5bf2a27718
ggml : remove src0 and src1 from ggml_tensor and rename opt to src (#2178)
|
%!s(int64=2) %!d(string=hai) anos |
 clyang
|
3bbc1a11f0
ggml : fix buidling with Intel MKL but ask for "cblas.h" issue (#2104) (#2115)
|
%!s(int64=2) %!d(string=hai) anos |
|
Qingyou Meng
|
1d656d6360
ggml : change ggml_graph_compute() API to not require context (#1999)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
7242140283
ggml : remove sched_yield() call in ggml_graph_compute_thread() (#2134)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
ec326d350c
ggml : fix bug introduced in #1237
|
%!s(int64=2) %!d(string=hai) anos |
 Stephan Walter
|
1b107b8550
ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
ed9a54e512
ggml : sync latest (new ops, macros, refactoring) (#2106)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
46088f7231
ggml : fix build with OpenBLAS (close #2066)
|
%!s(int64=2) %!d(string=hai) anos |
|
Qingyou Meng
|
b1ca8f36a9
ggml : disable GGML_TASK_INIT and GGML_TASK_FINALIZE by default (#1995)
|
%!s(int64=2) %!d(string=hai) anos |
 Erik Scholz
|
9d23589d63
fix pthreads setaffinity usage on android (#2020)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
d9779021bd
ggml : add support for ChatGLM RoPE
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
c824d2e368
ggml : avoid conv 2d kernel round up
|
%!s(int64=2) %!d(string=hai) anos |
 zrm
|
b853d45601
ggml : add NUMA support (#1556)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
bd34cdde38
ggml : sync latest ggml (custom operators)
|
%!s(int64=2) %!d(string=hai) anos |
 Robyn
|
5ec8dd5a3c
#1869 Fix null reference errors when training from scratch with CUDA (#1907)
|
%!s(int64=2) %!d(string=hai) anos |
 slaren
|
f2c754e1c3
ggml : improve ggml_graph_dump_dot, add ggml_format_name (#1978)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
18b35625c3
ggml : fix bug in LBFGS optimizer (found by ggml tests)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
b97ca431db
ggml : sync latest ggml repo (#1924)
|
%!s(int64=2) %!d(string=hai) anos |
 l3utterfly
|
8596af4277
ggml : fix bug in ggml_compute_forward_add_q_f32 (#1918)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
ce2c7d72e2
metal : handle buffers larger than device's maxBufferLength (#1826)
|
%!s(int64=2) %!d(string=hai) anos |
 Borislav Stanimirov
|
9cbf50c041
build : fix and ignore MSVC warnings (#1889)
|
%!s(int64=2) %!d(string=hai) anos |
 Johannes Gäßler
|
254a7a7a5f
CUDA full GPU acceleration, KV cache in VRAM (#1827)
|
%!s(int64=2) %!d(string=hai) anos |
 xaedes
|
e32089b2c2
train : improved training-from-scratch example (#1652)
|
%!s(int64=2) %!d(string=hai) anos |
