 Georgi Gerganov
|
d9d54e498d
speculative : refactor and add a simpler example (#10362)
|
пре 1 година |
 Xuan Son Nguyen
|
cda0e4b648
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
|
пре 1 година |
 Diego Devesa
|
7eee341bee
common : use common_ prefix for common library functions (#9805)
|
пре 1 година |
|
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
пре 1 година |
|
Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
пре 1 година |
|
Xuan Son Nguyen
|
bfe76d4a17
common : move arg parser code to `arg.cpp` (#9388)
|
пре 1 година |
|
Xuan Son Nguyen
|
1b9ae5189c
common : refactor arg parser (#9308)
|
пре 1 година |
|
Georgi Gerganov
|
df270ef745
llama : refactor sampling v2 (#9294)
|
пре 1 година |
 Liu Jia
|
0a4ce78681
common : Changed tuple to struct (TODO fix) (#8823)
|
пре 1 година |
 Johannes Gäßler
|
e02b597be3
lookup: fibonacci hashing, fix crashes (#8548)
|
пре 1 година |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
пре 1 година |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
пре 1 година |
|
Johannes Gäßler
|
28103f4832
Server: fix seed for multiple slots (#6835)
|
пре 1 година |
 Pedro Cuenca
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
пре 1 година |
 Jared Van Bortel
|
1b67731e18
BERT tokenizer fixes (#6498)
|
пре 1 година |
|
Johannes Gäßler
|
50ccaf5eac
lookup: complement data from context with general text statistics (#5479)
|
пре 1 година |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
пре 1 година |
|
Johannes Gäßler
|
e4640d8fdf
lookup: add print for drafting performance (#5450)
|
пре 1 година |
 LeonEricsson
|
7082d24cec
lookup : add prompt lookup decoding example (#4484)
|
пре 2 година |
