 Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
vor 1 Jahr |
|
Georgi Gerganov
|
152610eda9
server : output embeddings for all tokens when pooling = none (#10861)
|
vor 1 Jahr |
|
Georgi Gerganov
|
644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
|
vor 1 Jahr |
 Eric Curtin
|
c27ac678dd
Opt class for positional argument handling (#10508)
|
vor 1 Jahr |
 Xuan Son Nguyen
|
adffa6ffd5
common : improve -ctv -ctk CLI arguments (#10806)
|
vor 1 Jahr |
 Diego Devesa
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
Xuan Son Nguyen
|
9f912511bc
common : fix duplicated file name with hf_repo and hf_file (#10550)
|
vor 1 Jahr |
|
Diego Devesa
|
10bce0450f
llama : accept a list of devices to use to offload a model (#10497)
|
vor 1 Jahr |
|
Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
vor 1 Jahr |
|
Georgi Gerganov
|
d9d54e498d
speculative : refactor and add a simpler example (#10362)
|
vor 1 Jahr |
|
Georgi Gerganov
|
8e752a777b
llama : add check for KV cache shifts (#10401)
|
vor 1 Jahr |
 Johannes Gäßler
|
4e54be0ec6
llama/ex: remove --logdir argument (#10339)
|
vor 1 Jahr |
|
Diego Devesa
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
vor 1 Jahr |
|
Georgi Gerganov
|
5c333e0140
metal : add BF16 support (#8439)
|
vor 1 Jahr |
|
Diego Devesa
|
9f40989351
ggml : move CPU backend to a separate file (#10144)
|
vor 1 Jahr |
|
Georgi Gerganov
|
8d8ff71536
llama : remove Tail-Free sampling (#10071)
|
vor 1 Jahr |
 wwoodsTM
|
ff252ea48e
llama : add DRY sampler (#9702)
|
vor 1 Jahr |
 Michael Podvitskiy
|
d80fb71f8b
llama: string_split fix (#10022)
|
vor 1 Jahr |
|
Georgi Gerganov
|
f594bc80ba
ggml : add asserts for type conversion in fattn kernels (#9971)
|
vor 1 Jahr |
|
Xuan Son Nguyen
|
cda0e4b648
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
|
vor 1 Jahr |
 MaggotHATE
|
fbc98b748e
sampling : add XTC sampler (#9742)
|
vor 1 Jahr |
|
Georgi Gerganov
|
11ac9800af
llama : improve infill support and special token detection (#9798)
|
vor 1 Jahr |
|
Diego Devesa
|
7eee341bee
common : use common_ prefix for common library functions (#9805)
|
vor 1 Jahr |
|
Georgi Gerganov
|
8c475b97b8
rerank : use [SEP] token instead of [BOS] (#9737)
|
vor 1 Jahr |
 matiaslin
|
faac0bae26
common : ensure llama_batch size does not exceed max size (#9668)
|
vor 1 Jahr |
|
Georgi Gerganov
|
f4d2b8846a
llama : add reranking support (#9510)
|
vor 1 Jahr |
|
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
vor 1 Jahr |
|
Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
vor 1 Jahr |
 Ahmad Tameem
|
2b00fa7997
riscv : modify Makefile and add a RISCV_VECT to print log info (#9442)
|
vor 1 Jahr |
 Farbod Bijary
|
67155ab7f5
feat: Implements retrying logic for downloading models using --model-url flag (#9255)
|
vor 1 Jahr |
