thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

cli: new CLI experience (#17824)

Browse source 
* wip

* wip

* fix logging, add display info

* handle commands

* add args

* wip

* move old cli to llama-completion

* rm deprecation notice

* move server to a shared library

* move ci to llama-completion

* add loading animation

* add --show-timings arg

* add /read command, improve LOG_ERR

* add args for speculative decoding, enable show timings by default

* add arg --image and --audio

* fix windows build

* support reasoning_content

* fix llama2c workflow

* color default is auto

* fix merge conflicts

* properly fix color problem

Co-authored-by: bandoti <bandoti@users.noreply.github.com>

* better loading spinner

* make sure to clean color on force-exit

* also clear input files on "/clear"

* simplify common_log_flush

* add warning in mtmd-cli

* implement console writter

* fix data race

* add attribute

* fix llama-completion and mtmd-cli

* add some notes about console::log

* fix compilation

---------

Co-authored-by: bandoti <bandoti@users.noreply.github.com>
This commit is contained in:
Xuan-Son Nguyen 2025-12-10 15:28:59 +01:00 • committed by GitHub
parent b677721819
commit 6c2131773c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 742 additions and 148 deletions
Download patch file Download diff file Expand all files Collapse all files

12
tests/test-lora-conversion-inference.sh
View file

@ -79,19 +79,19 @@ run_conversion_and_inference_lora() {
# Run inference
echo -e "\n\n---------------------------\n\n"
echo "Running llama-cli without lora for $model_name with hidden_size $hidden_size..."
OUTPUT_BASE=$(./llama-cli -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
echo "Running llama-completion without lora for $model_name with hidden_size $hidden_size..."
OUTPUT_BASE=$(./llama-completion -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
-p "$EXPECTED_BASE_FIRST_WORD" -n 50 --seed 42 --temp 0)
echo -e "\n\n---------------------------\n\n"
echo "Running llama-cli with hot lora for $model_name with hidden_size $hidden_size..."
OUTPUT_LORA_HOT=$(./llama-cli -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
echo "Running llama-completion with hot lora for $model_name with hidden_size $hidden_size..."
OUTPUT_LORA_HOT=$(./llama-completion -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
--lora $MODELS_REPO/$model_name/hidden_size=$hidden_size/lora/Lora-F32-LoRA.gguf \
-p "$EXPECTED_LORA_FIRST_WORD" -n 50 --seed 42 --temp 0)
echo -e "\n\n---------------------------\n\n"
echo "Running llama-cli with merged lora for $model_name with hidden_size $hidden_size..."
OUTPUT_LORA_MERGED=$(./llama-cli -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32-lora-merged.gguf \
echo "Running llama-completion with merged lora for $model_name with hidden_size $hidden_size..."
OUTPUT_LORA_MERGED=$(./llama-completion -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32-lora-merged.gguf \
-p "$EXPECTED_LORA_FIRST_WORD" -n 50 --seed 42 --temp 0)
# Remove any initial white space