Xuan Son Nguyen 958367bf53 server : refactor slot input data, move tokenizer to HTTP thread (#10023) ...

* server : refactor slot input data, move tokenizer to HTTP thread

* move prompt_tokens.empty() check

* fix incorrect if branch

* fix infinite generation loop

* bring back infill validation

* add infill test

* try fixing format_infill

* fix test

* remove redundant code

* rename completion to inference

* update docs

* use llama_tokens everywhere

2024-10-24 21:51:22 +02:00

..

baby-llama

…

batched

…

batched-bench

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

batched.swift

…

convert-llama2c-to-ggml

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

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

cvector-generator

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

deprecation-warning

examples : remove finetune and train-text-from-scratch (#8669)

2024-07-25 10:39:04 +02:00

embedding

…

eval-callback

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

export-lora

…

gbnf-validator

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

gen-docs

…

gguf

gguf : handle null name during init (#8587)

2024-07-20 17:15:42 +03:00

gguf-hash

gguf-hash : update clib.json to point to original xxhash repo (#8491)

2024-07-16 10:14:16 +03:00

gguf-split

…

gritlm

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

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

imatrix

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

infill

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

jeopardy

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)

2024-06-13 00:41:52 +01:00

llama-bench

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

llama.android

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

llama.swiftui

llama : default sampling changes + greedy update (#9897)

2024-10-21 09:46:40 +03:00

llava

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

lookahead

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

lookup

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

main

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

main-cmake-pkg

Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)

2024-07-02 12:18:10 -04:00

parallel

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

passkey

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

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

perplexity

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +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

…

rpc

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

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

save-load-state

llama : default sampling changes + greedy update (#9897)

2024-10-21 09:46:40 +03:00

server

server : refactor slot input data, move tokenizer to HTTP thread (#10023)

2024-10-24 21:51:22 +02:00

simple

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

2024-10-18 23:18:01 +02:00

speculative

llama : default sampling changes + greedy update (#9897)

2024-10-21 09:46:40 +03:00

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

…

convert_legacy_llama.py

…

json_schema_pydantic_example.py

…

json_schema_to_grammar.py

…

llama.vim

llama.vim : bump generation time limit to 3s [no ci]

2024-10-23 17:16:56 +03:00

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

…