Djip007 19d8762ab6 ggml : refactor online repacking (#10446) ... * rename ggml-cpu-aarch64.c to .cpp * reformat extra cpu backend. - clean Q4_0_N_M and IQ4_0_N_M - remove from "file" tensor type - allow only with dynamic repack - extract cpu extra bufts and convert to C++ - hbm - "aarch64" - more generic use of extra buffer - generalise extra_supports_op - new API for "cpu-accel": - amx - aarch64 * clang-format * Clean Q4_0_N_M ref Enable restrict on C++ * add op GGML_OP_MUL_MAT_ID for Q4_0_N_M with runtime repack * added/corrected control on tensor size for Q4 repacking. * Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * add debug logs on repacks. --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>		2024-12-07 14:37:50 +02:00
..
batched	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
batched-bench	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
batched.swift
convert-llama2c-to-ggml	make : deprecate (#10514)	2024-12-02 21:22:53 +02:00
cvector-generator	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
deprecation-warning	Update deprecation-warning.cpp (#10619)	2024-12-04 23:19:20 +01:00
embedding	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
eval-callback	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
export-lora	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
gbnf-validator	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
gen-docs	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
gguf	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
gguf-hash	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
gguf-split	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
gritlm	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
imatrix	make : deprecate (#10514)	2024-12-02 21:22:53 +02:00
infill	readme : add option, update default value, fix formatting (#10271)	2024-12-03 12:50:08 +02:00
jeopardy
llama-bench	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
llama.android
llama.swiftui	llama : default sampling changes + greedy update (#9897)	2024-10-21 09:46:40 +03:00
llava	clip : add sycl support (#10574)	2024-12-04 01:26:37 +01:00
lookahead	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
lookup	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
main	readme : add option, update default value, fix formatting (#10271)	2024-12-03 12:50:08 +02:00
main-cmake-pkg	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
parallel	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
passkey	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
perplexity	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
quantize	ggml : refactor online repacking (#10446)	2024-12-07 14:37:50 +02:00
quantize-stats	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
retrieval	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
rpc	ggml : move CPU backend to a separate file (#10144)	2024-11-03 19:34:08 +01:00
run	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
save-load-state	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
server	server : fix free of spec context and batch (#10651)	2024-12-07 11:52:44 +02:00
simple	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
simple-chat	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
speculative	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
speculative-simple	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
sycl
tokenize	ggml : move AMX to the CPU backend (#10570)	2024-11-29 21:54:58 +01:00
chat-13B.bat
chat-13B.sh
chat-persistent.sh	scripts : fix pattern and get n_tokens in one go (#10221)	2024-11-09 09:06:54 +02:00
chat-vicuna.sh
chat.sh
CMakeLists.txt	cmake : enable warnings in llama (#10474)	2024-11-26 14:18:08 +02:00
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
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.py
pydantic_models_to_grammar_examples.py
reason-act.sh
regex_to_grammar.py
server-llama2-13B.sh
server_embd.py
ts-type-to-grammar.sh