 Bono Lv
|
c574bddb36
fix a typo in examples/server/README.md (#2478)
|
2 years ago |
 ebraminio
|
86aeb27734
server : Support dark mode (#2414)
|
2 years ago |
 Matteo Boschini
|
1873ff586b
metal : add gqa8 kernel to allow llama-2-70B on metal (#2459)
|
2 years ago |
 Johannes Gäßler
|
49e7cb5bb1
CUDA: fixed LLAMA_FAST compilation option (#2473)
|
2 years ago |
|
Johannes Gäßler
|
b772bba42e
CUDA: fixed cmake F16 option (#2471)
|
2 years ago |
|
Johannes Gäßler
|
0728c5a8b9
CUDA: mmq CLI option, fixed mmq build issues (#2453)
|
2 years ago |
|
Johannes Gäßler
|
1215ed7d5c
CUDA: Implemented row flattening for non-glm RoPE (#2468)
|
2 years ago |
|
Johannes Gäßler
|
2dbf518911
CUDA: fewer memory bank conflicts for mul_mat_q (#2458)
|
2 years ago |
 slaren
|
9d2382b3e4
Fix Metal backend broken from the allocator changes (#2455)
|
2 years ago |
|
slaren
|
a113689571
ggml : add graph tensor allocator (#2411)
|
2 years ago |
|
Johannes Gäßler
|
11f3ca06b8
CUDA: Quantized matrix matrix multiplication (#2160)
|
2 years ago |
|
Johannes Gäßler
|
9baf9ef304
CUDA: faster multi GPU synchronization (#2448)
|
2 years ago |
 klosax
|
8a88e5855c
perplexity : add Hellaswag calculation (#2389)
|
2 years ago |
 Lee
|
a9559bf77b
ggml : workaround for missing _mm256_setr_m128i in GCC < 8 in k_quants.c (#2405)
|
2 years ago |
 eric8607242
|
ee1b497c98
llama : support more diverse tokenizers? (#2420)
|
2 years ago |
 Georgi Gerganov
|
d73b8d48b4
examples : fix whitespace
|
2 years ago |
 nhamanasu
|
34ae1caf7f
examples : server chat mode with llama2 (#2400)
|
2 years ago |
 Weird Constructor
|
d91f3f0c55
readme : fix the description of the Tail free sampling (TFS) method (#2431)
|
2 years ago |
 Rand Xie
|
65cdf34bdc
llama : use n_embd_gqa instead of n_embd to handle llama-2 70B (#2433)
|
2 years ago |
 niansa/tuxifan
|
edcc7ae7d2
Obtaining LLaMA 2 instructions (#2308)
|
2 years ago |
 mj-shifu
|
7c529cede6
convert.py : Update to support 70B HF format model files (#2427)
|
2 years ago |
|
Georgi Gerganov
|
1a941869cb
metal : disable graph concurrency optimization due to bug (#2413)
|
2 years ago |
|
slaren
|
b5472ea0ad
ggml : fix assert in ggml_set_unary_op (#2410)
|
2 years ago |
 Cebtenzzre
|
6df1f5940f
make : build with -Wmissing-prototypes (#2394)
|
2 years ago |
|
slaren
|
5488fb789e
ggml : allocate graphs in a context (#2392)
|
2 years ago |
 Kawrakow
|
eb542d3932
Add LLAMA_DEFAULT_RMS_EPS so we can change the default (#2384)
|
2 years ago |
|
slaren
|
07aaa0f63f
ggml : fix ggml_flash_attn to use op_params (#2387)
|
2 years ago |
 ldwang
|
fce48caf9a
convert.py : support bpe tokenizer (#2228)
|
2 years ago |
 Jiahao Li
|
875086bdb9
ggml : relax contiguous constraints in activation function (#2371)
|
2 years ago |
|
slaren
|
da1889834a
ggml : improve graph build time via hash table lookup (#2329)
|
2 years ago |
