 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 |
 Hesen Peng
|
82552b7f54
build : fix line breaking error in build-info.sh (#2349)
|
2 years ago |
 Xiao-Yong Jin
|
0c06204fb3
main : add `--in-prefix-bos` to prefix BOS to user inputs; keep EOS (#2304)
|
2 years ago |
 Eve
|
1fed755b1f
ci : add non-AVX scalar build/test (#2356)
|
2 years ago |
 katsu560
|
be2301bcda
k_quants : add AVX support to dot functions with QK_K as 64 (#2339)
|
2 years ago |
 Shouzheng Liu
|
1aa18ef994
metal : concurrently dispatch commands (#2358)
|
2 years ago |
|
Kawrakow
|
9a08eaf3c4
Another speed gain for Q4_0 and Q4_1 on Metal (#2375)
|
2 years ago |
|
Kawrakow
|
129d844c87
Fix Q4_K and Q5_K for QK_K = 64 on CUDA (#2359)
|
2 years ago |
|
slaren
|
d5512b782b
server: add rms_norm_eps parameter (#2380)
|
2 years ago |
 Henri Vasserman
|
c798308e3a
[Server] Escape HTML in webchat (#2368)
|
2 years ago |
|
slaren
|
41c674161f
make rms_norm_eps a parameter (#2374)
|
2 years ago |
 Aarni Koskela
|
b3f138d058
Chat UI extras (#2366)
|
2 years ago |
|
Georgi Gerganov
|
5b2b2dc6ae
ggml : sync (unary ops refactor, static-correctness) (#2370)
|
2 years ago |
|
Kawrakow
|
42f70cb2f6
Fix scalar version of Q5_K when QK_K = 64 (#2362)
|
2 years ago |
 Evan Jones
|
84e09a7d8b
llama : add grammar-based sampling (#1773)
|
2 years ago |
|
Kawrakow
|
2f9cf974a0
Some more Q4_K and Q5_K speedup on CUDA (#2346)
|
2 years ago |
 IgnacioFDM
|
4f06592cc6
Add gqa parameter support to the server (#2351)
|
2 years ago |
 Johannes Gäßler
|
70d26ac388
Fix __dp4a documentation (#2348)
|
2 years ago |
 wzy
|
57921ca6db
common : n_threads == -1 uses std::thread::hardware_concurrency() (#2347)
|
2 years ago |
|
slaren
|
3602ac4255
fix n_tasks (#2342)
|
2 years ago |
