Georgi Gerganov 2b3389677a

ggml : refactor rope norm/neox (#7634) ...

* ggml : unify rope norm/neox (CPU)

* ggml : fix compile warning

* ggml : remove GLM rope mode

ggml-ci

* metal : better rope implementation

ggml-ci

* cuda : better rope implementation

ggml-ci

* naming : n_orig_ctx -> n_ctx_orig

ggml-ci

* dev : add reminders to update backends

ggml-ci

* vulkan : fix ggml_rope_ext() usage

* cuda : fix array size + indents

ggml-ci

2024-06-05 11:29:20 +03:00

..

baby-llama

ggml : refactor rope norm/neox (#7634)

2024-06-05 11:29:20 +03:00

batched

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

batched-bench

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

batched.swift

…

benchmark

…

convert-llama2c-to-ggml

train : change default FA argument (#7528)

2024-05-25 15:22:35 +03:00

embedding

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

eval-callback

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

export-lora

…

finetune

ggml : refactor rope norm/neox (#7634)

2024-06-05 11:29:20 +03:00

gbnf-validator

…

gguf

…

gguf-split

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

gritlm

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

imatrix

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

infill

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

jeopardy

…

llama-bench

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

llama.android

android : module (#7502)

2024-05-25 11:11:33 +03:00

llama.swiftui

…

llava

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

lookahead

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

lookup

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

main

readme : remove -ins (#7759)

2024-06-05 09:40:49 +03:00

main-cmake-pkg

ggml : remove OpenCL (#7735)

2024-06-04 21:23:20 +03:00

parallel

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

passkey

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

perplexity

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

quantize

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

quantize-stats

…

retrieval

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

rpc

[SYCL] Update rpc-server.cpp to include SYCL backend (#7682)

2024-06-02 12:13:54 +03:00

save-load-state

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

server

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

simple

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

speculative

common : refactor cli arg parsing (#7675)

2024-06-04 21:23:39 +03:00

sycl

add build shared lib in win release package (#7438)

2024-05-24 10:06:56 +08:00

tokenize

Make tokenize CLI tool have nicer command line arguments. (#6188)

2024-05-25 11:14:42 +10:00

train-text-from-scratch

ggml : refactor rope norm/neox (#7634)

2024-06-05 11:29:20 +03:00

alpaca.sh

…

base-translate.sh

…

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

…

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

llama : remove beam search (#7736)

2024-06-04 21:23:05 +03:00

convert-legacy-llama.py

ggml : refactor rope norm/neox (#7634)

2024-06-05 11:29:20 +03:00

gpt4all.sh

…

json_schema_to_grammar.py

…

json-schema-pydantic-example.py

…

llama2-13b.sh

…

llama2.sh

…

llama.vim

…

llm.vim

…

Miku.sh

…

pydantic_models_to_grammar.py

…

pydantic-models-to-grammar-examples.py

…

reason-act.sh

…

regex-to-grammar.py

…

server-embd.py

…

server-llama2-13B.sh

…

ts-type-to-grammar.sh

…