 Qingyou Meng
|
1d656d6360
ggml : change ggml_graph_compute() API to not require context (#1999)
|
2 years ago |
 Georgi Gerganov
|
7242140283
ggml : remove sched_yield() call in ggml_graph_compute_thread() (#2134)
|
2 years ago |
|
Georgi Gerganov
|
ec326d350c
ggml : fix bug introduced in #1237
|
2 years ago |
 Stephan Walter
|
1b107b8550
ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)
|
2 years ago |
|
Georgi Gerganov
|
ed9a54e512
ggml : sync latest (new ops, macros, refactoring) (#2106)
|
2 years ago |
|
Georgi Gerganov
|
46088f7231
ggml : fix build with OpenBLAS (close #2066)
|
2 years ago |
|
Qingyou Meng
|
b1ca8f36a9
ggml : disable GGML_TASK_INIT and GGML_TASK_FINALIZE by default (#1995)
|
2 years ago |
 Erik Scholz
|
9d23589d63
fix pthreads setaffinity usage on android (#2020)
|
2 years ago |
|
Georgi Gerganov
|
d9779021bd
ggml : add support for ChatGLM RoPE
|
2 years ago |
|
Georgi Gerganov
|
c824d2e368
ggml : avoid conv 2d kernel round up
|
2 years ago |
 zrm
|
b853d45601
ggml : add NUMA support (#1556)
|
2 years ago |
|
Georgi Gerganov
|
bd34cdde38
ggml : sync latest ggml (custom operators)
|
2 years ago |
 Robyn
|
5ec8dd5a3c
#1869 Fix null reference errors when training from scratch with CUDA (#1907)
|
2 years ago |
 slaren
|
f2c754e1c3
ggml : improve ggml_graph_dump_dot, add ggml_format_name (#1978)
|
2 years ago |
|
Georgi Gerganov
|
18b35625c3
ggml : fix bug in LBFGS optimizer (found by ggml tests)
|
2 years ago |
|
Georgi Gerganov
|
b97ca431db
ggml : sync latest ggml repo (#1924)
|
2 years ago |
 l3utterfly
|
8596af4277
ggml : fix bug in ggml_compute_forward_add_q_f32 (#1918)
|
2 years ago |
|
Georgi Gerganov
|
ce2c7d72e2
metal : handle buffers larger than device's maxBufferLength (#1826)
|
2 years ago |
 Borislav Stanimirov
|
9cbf50c041
build : fix and ignore MSVC warnings (#1889)
|
2 years ago |
 Johannes Gäßler
|
254a7a7a5f
CUDA full GPU acceleration, KV cache in VRAM (#1827)
|
2 years ago |
 xaedes
|
e32089b2c2
train : improved training-from-scratch example (#1652)
|
2 years ago |
 Kerfuffle
|
74d4cfa343
Allow "quantizing" to f16 and f32 (#1787)
|
2 years ago |
|
Georgi Gerganov
|
17c10acfb4
ggml : force no_alloc == false when creating opt tensors (close #1699)
|
2 years ago |
 Xingchen Song(宋星辰)
|
ef3171d162
ggml : workaround for missing _mm256_setr_m128i in GCC < 8 (#1638)
|
2 years ago |
 Steven Roussey
|
b50b570ed9
ggml : fix fprintf warnings (#1720)
|
2 years ago |
|
Georgi Gerganov
|
5c64a0952e
k-quants : allow to optionally disable at compile time (#1734)
|
2 years ago |
|
Georgi Gerganov
|
2a4e41a086
llama : fix compile warnings
|
2 years ago |
|
Johannes Gäßler
|
17366df842
Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703)
|
2 years ago |
|
Georgi Gerganov
|
2d43387daf
ggml : fix builds, add ggml-quants-k.o (close #1712, close #1710)
|
2 years ago |
 kiltyj
|
9d0693bce3
metal : use shared buffers between CPU and GPU (#1696)
|
2 years ago |
