Xuan-Son Nguyen 96e1280839 clip : bring back GPU support (#12322) ...

* clip : bring back GPU support

* use n_gpu_layers param

* fix double free

* ggml_backend_init_by_type

* clean up

2025-03-11 09:20:16 +01:00

..

batched

…

batched-bench

…

batched.swift

…

convert-llama2c-to-ggml

…

cvector-generator

common : refactor '-o' option (#12278)

2025-03-10 13:34:13 +02:00

deprecation-warning

…

embedding

…

eval-callback

…

export-lora

common : refactor '-o' option (#12278)

2025-03-10 13:34:13 +02:00

gbnf-validator

…

gen-docs

…

gguf

…

gguf-hash

…

gguf-split

…

gritlm

…

imatrix

common : refactor '-o' option (#12278)

2025-03-10 13:34:13 +02:00

infill

…

jeopardy

…

llama-bench

…

llama.android

android : fix KV cache log message condition (#12212)

2025-03-06 08:22:49 +02:00

llama.swiftui

…

llava

clip : bring back GPU support (#12322)

2025-03-11 09:20:16 +01:00

lookahead

…

lookup

…

main

…

parallel

…

passkey

…

perplexity

…

quantize

ggml : portability fixes for VS 2017 (#12150)

2025-03-04 18:53:26 +02:00

quantize-stats

…

retrieval

…

rpc

…

run

…

save-load-state

…

server

tool-call: ensure there's always a non-empty tool call id (#12292)

2025-03-10 09:45:29 +00:00

simple

…

simple-chat

…

simple-cmake-pkg

…

speculative

…

speculative-simple

…

sycl

…

tokenize

…

tts

…

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

…

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

…

convert_legacy_llama.py

metadata: Detailed Dataset Authorship Metadata (#8875)

2024-11-13 21:10:38 +11:00

json_schema_pydantic_example.py

…

json_schema_to_grammar.py

tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)

2025-03-05 13:05:13 +00:00

llama.vim

…

llm.vim

…

Miku.sh

…

pydantic_models_to_grammar_examples.py

…

pydantic_models_to_grammar.py

…

reason-act.sh

…

regex_to_grammar.py

…

server_embd.py

…

server-llama2-13B.sh

…

ts-type-to-grammar.sh

…