 slaren
|
e7e4df031b
llama : ggml-backend integration (#4766)
|
2 лет назад |
 howlger
|
4315a94366
common : streamline the formatting of help (#4890)
|
2 лет назад |
 Georgi Gerganov
|
f445c0e68c
llama : fix llm_build_k_shift to use correct n_rot (#4889)
|
2 лет назад |
|
Georgi Gerganov
|
7edefbd79c
main : better name for variable n_print (#4874)
|
2 лет назад |
|
Georgi Gerganov
|
3ca63b4538
main : disable token count by default (#4874)
|
2 лет назад |
 pudepiedj
|
43f76bf1c3
main : print total token count and tokens consumed so far (#4874)
|
2 лет назад |
|
howlger
|
1fc2f265ff
common : fix the short form of `--grp-attn-w`, not `-gat` (#4825)
|
2 лет назад |
|
Georgi Gerganov
|
52531fdff8
main : add self-extend support (#4815)
|
2 лет назад |
 automaticcat
|
24a447e20a
ggml : add ggml_cpu_has_avx_vnni() (#4589)
|
2 лет назад |
 Jared Van Bortel
|
8fe03ffdda
common : remove incorrect --model-draft default (#4568)
|
2 лет назад |
 Siwen Yu
|
9fb13f9584
common : add `--version` option to show build info in CLI (#4433)
|
2 лет назад |
|
Georgi Gerganov
|
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
|
2 лет назад |
 Kerfuffle
|
5aa365d88f
llama : allow overriding GGUF metadata when loading model (#4092)
|
2 лет назад |
 MaggotHATE
|
52c8bc3cf3
sampling : custom samplers order (#4285)
|
2 лет назад |
|
Georgi Gerganov
|
6b0a7420d0
llama : KV cache view API + better KV cache management (#4170)
|
2 лет назад |
 Seb C
|
881800d1f0
main : Add ChatML functionality to main example (#4046)
|
2 лет назад |
 kchro3
|
262005ad9d
common : comma should be semicolon (#4137)
|
2 лет назад |
 Jannis Schönleber
|
9e87ef60e1
common : improve yaml log escaping (#4080)
|
2 лет назад |
|
Kerfuffle
|
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
|
2 лет назад |
|
slaren
|
2833a6f63c
ggml-cuda : fix f16 mul mat (#3961)
|
2 лет назад |
|
Kerfuffle
|
d9ccce2e33
Allow common process_escapes to handle \x sequences (#3928)
|
2 лет назад |
|
Georgi Gerganov
|
8f961abdc4
speculative : change default p_accept to 0.5 + CLI args (#3919)
|
2 лет назад |
 cebtenzzre
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
2 лет назад |
|
cebtenzzre
|
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
|
2 лет назад |
|
Georgi Gerganov
|
ff8f9a88da
common : minor (#3715)
|
2 лет назад |
 bandoti
|
0e40806c1c
common : allow caller to handle help/argument exceptions (#3715)
|
2 лет назад |
 kalomaze
|
238657db23
samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841)
|
2 лет назад |
|
Kerfuffle
|
6e08281e58
Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843)
|
2 лет назад |
|
Georgi Gerganov
|
ee1a0ec9cb
llama : add option for greedy sampling with probs (#3813)
|
2 лет назад |
 Henk Poley
|
177461104b
common : print that one line of the syntax help *also* to standard output (#3823)
|
2 лет назад |
