| .. |
|
batched
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
batched-bench
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
batched.swift
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
vor 1 Jahr |
|
convert-llama2c-to-ggml
|
8648c52101
make : deprecate (#10514)
|
vor 1 Jahr |
|
cvector-generator
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
deprecation-warning
|
f112d198cd
Update deprecation-warning.cpp (#10619)
|
vor 1 Jahr |
|
embedding
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
eval-callback
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
export-lora
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
gbnf-validator
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
gen-docs
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
gguf
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
gguf-hash
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
gguf-split
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
vor 1 Jahr |
|
gritlm
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
imatrix
|
8648c52101
make : deprecate (#10514)
|
vor 1 Jahr |
|
infill
|
82bca2257b
readme : add option, update default value, fix formatting (#10271)
|
vor 1 Jahr |
|
jeopardy
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
vor 1 Jahr |
|
llama-bench
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
vor 1 Jahr |
|
llama.android
|
cda0e4b648
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
|
vor 1 Jahr |
|
llama.swiftui
|
43ed389a3f
llama : use cmake for swift build (#10525)
|
vor 1 Jahr |
|
llava
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
vor 1 Jahr |
|
lookahead
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
lookup
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
main
|
82bca2257b
readme : add option, update default value, fix formatting (#10271)
|
vor 1 Jahr |
|
main-cmake-pkg
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
parallel
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
passkey
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
perplexity
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
quantize
|
1a31d0dc00
Update README.md (#10772)
|
vor 1 Jahr |
|
quantize-stats
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
retrieval
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
vor 1 Jahr |
|
rpc
|
9f40989351
ggml : move CPU backend to a separate file (#10144)
|
vor 1 Jahr |
|
run
|
c27ac678dd
Opt class for positional argument handling (#10508)
|
vor 1 Jahr |
|
save-load-state
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
server
|
89d604f2c8
server: Fix `has_next_line` in JSON response (#10818)
|
vor 1 Jahr |
|
simple
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
simple-chat
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
speculative
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
speculative-simple
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
vor 1 Jahr |
|
sycl
|
faf67b3de4
[SYCL]set context default value to avoid memory issue, update guide (#9476)
|
vor 1 Jahr |
|
tokenize
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
vor 1 Jahr |
|
CMakeLists.txt
|
adffa6ffd5
common : improve -ctv -ctk CLI arguments (#10806)
|
vor 1 Jahr |
|
Miku.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
vor 1 Jahr |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
vor 2 Jahren |
|
chat-13B.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
vor 1 Jahr |
|
chat-persistent.sh
|
8fc393f246
scripts : fix pattern and get n_tokens in one go (#10221)
|
vor 1 Jahr |
|
chat-vicuna.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
vor 1 Jahr |
|
chat.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
vor 1 Jahr |
|
convert_legacy_llama.py
|
a0ec17b32e
metadata: Detailed Dataset Authorship Metadata (#8875)
|
vor 1 Jahr |
|
json_schema_pydantic_example.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
vor 1 Jahr |
|
json_schema_to_grammar.py
|
66c2c93082
grammar : fix JSON Schema for string regex with top-level alt. (#9903)
|
vor 1 Jahr |
|
llama.vim
|
2d3aba9ee8
llama.vim : bump generation time limit to 3s [no ci]
|
vor 1 Jahr |
|
llm.vim
|
ad9ddcff6e
llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)
|
vor 2 Jahren |
|
pydantic_models_to_grammar.py
|
090fca7a07
pydantic : replace uses of __annotations__ with get_type_hints (#8474)
|
vor 1 Jahr |
|
pydantic_models_to_grammar_examples.py
|
22f281aa16
examples : Rewrite pydantic_models_to_grammar_examples.py (#8493)
|
vor 1 Jahr |
|
reason-act.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
vor 1 Jahr |
|
regex_to_grammar.py
|
e235b267a2
py : switch to snake_case (#8305)
|
vor 1 Jahr |
|
server-llama2-13B.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
vor 1 Jahr |
|
server_embd.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
vor 1 Jahr |
|
ts-type-to-grammar.sh
|
ab9a3240a9
JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)
|
vor 1 Jahr |
Michelle Tan
89d604f2c8
server: Fix `has_next_line` in JSON response (#10818)