Ed Addario 71e90e8813 quantize: Handle user-defined quantization levels for additional tensors (#12511) ... * Add llama_model_quantize_params parameters * Add new quantize parameters parsing and validation * Update usage * Add new parameters defaults * Add new quantization parameters logic * Add llama_model_quantize_params parameters * Add new quantize parameters parsing and validation * Update usage * Add new parameters defaults * Add new quantization parameters logic * Minor refactoring as per the contributors' coding guidelines * Update descriptions to match existing style * Add llama_model_quantize_params parameters * Add new quantize parameters parsing and validation * Update usage * Add new parameters defaults * Add new quantization parameters logic * Minor refactoring as per the contributors' guidelines * Implement general --tensor-type instead of tensor-specific command option * Fix implied type bug * Restore missing #includes * Add regex capability for tensor selection * Refactor function name and update ALLOWED_TENSOR_TYPE * Add missing #include * Handle edge case when tensor name is cls.output * Minor logging improvement		2025-04-13 21:29:28 +03:00
..
batched	common : refactor downloading system, handle mmproj with -hf option (#12694)	2025-04-01 23:44:05 +02:00
batched-bench	common : refactor downloading system, handle mmproj with -hf option (#12694)	2025-04-01 23:44:05 +02:00
batched.swift
convert-llama2c-to-ggml
cvector-generator
deprecation-warning
embedding
eval-callback
export-lora	common : refactor downloading system, handle mmproj with -hf option (#12694)	2025-04-01 23:44:05 +02:00
gbnf-validator
gen-docs
gguf
gguf-hash
gguf-split	gguf-split : --merge now respects --dry-run option (#12681)	2025-04-04 16:09:12 +02:00
gritlm	common : refactor downloading system, handle mmproj with -hf option (#12694)	2025-04-01 23:44:05 +02:00
imatrix
infill
jeopardy
llama-bench
llama.android	cmake : enable curl by default (#12761)	2025-04-07 13:35:19 +02:00
llama.swiftui
llava	llava: Fix cpu-only clip image encoding sefault (#12907)	2025-04-12 07:29:03 +02:00
lookahead
lookup
main	docs : bring llama-cli conversation/template docs up-to-date (#12426)	2025-03-17 21:14:32 +01:00
parallel	llama : refactor kv cache guard (#12695)	2025-04-02 14:32:59 +03:00
passkey	common : refactor downloading system, handle mmproj with -hf option (#12694)	2025-04-01 23:44:05 +02:00
perplexity	hellaswag: display estimated score confidence interval (#12797)	2025-04-07 18:47:08 +03:00
quantize	quantize: Handle user-defined quantization levels for additional tensors (#12511)	2025-04-13 21:29:28 +03:00
quantize-stats
retrieval
rpc	common : Define cache directory on AIX (#12915)	2025-04-12 17:33:39 +02:00
run	contrib: support modelscope community (#12664)	2025-04-11 14:01:56 +02:00
save-load-state
server	server : add VSCode's Github Copilot Chat support (#12896)	2025-04-11 23:37:41 +03:00
simple
simple-chat
simple-cmake-pkg
speculative	common : refactor downloading system, handle mmproj with -hf option (#12694)	2025-04-01 23:44:05 +02:00
speculative-simple	common : refactor downloading system, handle mmproj with -hf option (#12694)	2025-04-01 23:44:05 +02:00
sycl	cmake : enable curl by default (#12761)	2025-04-07 13:35:19 +02:00
tokenize
tts	common : refactor downloading system, handle mmproj with -hf option (#12694)	2025-04-01 23:44:05 +02:00
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
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	llama : fix FA when KV cache is not used (i.e. embeddings) (#12825)	2025-04-08 19:54:51 +03:00
ts-type-to-grammar.sh