Georgi Gerganov 223c25a72f server : improve infill context reuse (#9894) ...

ggml-ci

2024-10-15 16:28:55 +03:00

..

baby-llama

…

batched

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

batched-bench

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

batched.swift

llama : llama_perf + option to disable timings during decode (#9355)

2024-09-13 09:53:38 +03:00

convert-llama2c-to-ggml

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

cvector-generator

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

deprecation-warning

…

embedding

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

eval-callback

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

export-lora

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

gbnf-validator

…

gen-docs

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

gguf

…

gguf-hash

…

gguf-split

gguf-split : improve --split and --merge logic (#9619)

2024-10-02 10:21:57 +03:00

gritlm

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

imatrix

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

infill

llama : improve infill support and special token detection (#9798)

2024-10-12 08:21:51 +03:00

jeopardy

…

llama-bench

rpc : add backend registry / device interfaces (#9812)

2024-10-10 20:14:55 +02:00

llama.android

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

llama.swiftui

…

llava

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

lookahead

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

lookup

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

main

sampling : add XTC sampler (#9742)

2024-10-15 12:54:55 +02:00

main-cmake-pkg

…

parallel

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

passkey

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

perplexity

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

quantize

quantize : improve type name parsing (#9570)

2024-09-20 20:55:36 +02:00

quantize-stats

ggml : fix BLAS with unsupported types (#9775)

2024-10-08 14:21:43 +02:00

retrieval

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

rpc

rpc : add backend registry / device interfaces (#9812)

2024-10-10 20:14:55 +02:00

save-load-state

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

server

server : improve infill context reuse (#9894)

2024-10-15 16:28:55 +03:00

simple

examples : do not use common library in simple example (#9803)

2024-10-10 19:50:49 +02:00

speculative

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

sycl

[SYCL]set context default value to avoid memory issue, update guide (#9476)

2024-09-18 08:30:31 +08:00

tokenize

common : use common_ prefix for common library functions (#9805)

2024-10-10 22:57:42 +02:00

base-translate.sh

…

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

…

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

examples : remove benchmark (#9704)

2024-10-02 10:14:44 +03:00

convert_legacy_llama.py

…

json_schema_pydantic_example.py

…

json_schema_to_grammar.py

…

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

…