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

* `main`/`server`: rename to `llama` / `llama-server` for consistency w/ homebrew

* server: update refs -> llama-server

gitignore llama-server

* server: simplify nix package

* main: update refs -> llama

fix examples/main ref

* main/server: fix targets

* update more names

* Update build.yml

* rm accidentally checked in bins

* update straggling refs

* Update .gitignore

* Update server-llm.sh

* main: target name -> llama-cli

* Prefix all example bins w/ llama-

* fix main refs

* rename {main->llama}-cmake-pkg binary

* prefix more cmake targets w/ llama-

* add/fix gbnf-validator subfolder to cmake

* sort cmake example subdirs

* rm bin files

* fix llama-lookup-* Makefile rules

* gitignore /llama-*

* rename Dockerfiles

* rename llama|main -> llama-cli; consistent RPM bin prefixes

* fix some missing -cli suffixes

* rename dockerfile w/ llama-cli

* rename(make): llama-baby-llama

* update dockerfile refs

* more llama-cli(.exe)

* fix test-eval-callback

* rename: llama-cli-cmake-pkg(.exe)

* address gbnf-validator unused fread warning (switched to C++ / ifstream)

* add two missing llama- prefixes

* Updating docs for eval-callback binary to use new `llama-` prefix.

* Updating a few lingering doc references for rename of main to llama-cli

* Updating `run-with-preset.py` to use new binary names.
Updating docs around `perplexity` binary rename.

* Updating documentation references for lookup-merge and export-lora

* Updating two small `main` references missed earlier in the finetune docs.

* Update apps.nix

* update grammar/README.md w/ new llama-* names

* update llama-rpc-server bin name + doc

* Revert "update llama-rpc-server bin name + doc"

This reverts commit e474ef1df481fd8936cd7d098e3065d7de378930.

* add hot topic notice to README.md

* Update README.md

* Update README.md

* rename gguf-split & quantize bins refs in **/tests.sh

---------

Co-authored-by: HanClinto <hanclinto@gmail.com>

10 files changed, 49 insertions, 49 deletions

diff --git a/scripts/get-hellaswag.sh b/scripts/get-hellaswag.sh
index 121979fe..4e1b1cc1 100755
--- a/scripts/get-hellaswag.sh
+++ b/scripts/get-hellaswag.sh
@@ -4,7 +4,7 @@ wget https://raw.githubusercontent.com/klosax/hellaswag_text_data/main/hellaswag
 
 echo "Usage:"
 echo ""
-echo "  ./perplexity -m model.gguf -f hellaswag_val_full.txt --hellaswag [--hellaswag-tasks N] [other params]"
+echo "  ./llama-perplexity -m model.gguf -f hellaswag_val_full.txt --hellaswag [--hellaswag-tasks N] [other params]"
 echo ""
 
 exit 0
diff --git a/scripts/get-wikitext-103.sh b/scripts/get-wikitext-103.sh
index 880dd5cb..9c65fafb 100755
--- a/scripts/get-wikitext-103.sh
+++ b/scripts/get-wikitext-103.sh
@@ -4,7 +4,7 @@ wget https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-103-raw-v1.
 
 echo "Usage:"
 echo ""
-echo "  ./perplexity -m model.gguf -f wiki.test.raw [other params]"
+echo "  ./llama-perplexity -m model.gguf -f wiki.test.raw [other params]"
 echo ""
 
 exit 0
diff --git a/scripts/get-wikitext-2.sh b/scripts/get-wikitext-2.sh
index b01476a4..5f3845ef 100755
--- a/scripts/get-wikitext-2.sh
+++ b/scripts/get-wikitext-2.sh
@@ -5,7 +5,7 @@ unzip wikitext-2-raw-v1.zip
 
 echo "Usage:"
 echo ""
-echo "  ./perplexity -m model.gguf -f wikitext-2-raw/wiki.test.raw [other params]"
+echo "  ./llama-perplexity -m model.gguf -f wikitext-2-raw/wiki.test.raw [other params]"
 echo ""
 
 exit 0
diff --git a/scripts/get-winogrande.sh b/scripts/get-winogrande.sh
index 5f234468..f1fc0e2d 100755
--- a/scripts/get-winogrande.sh
+++ b/scripts/get-winogrande.sh
@@ -4,7 +4,7 @@ wget https://huggingface.co/datasets/ikawrakow/winogrande-eval-for-llama.cpp/raw
 
 echo "Usage:"
 echo ""
-echo "  ./perplexity -m model.gguf -f winogrande-debiased-eval.csv --winogrande [--winogrande-tasks N] [other params]"
+echo "  ./llama-perplexity -m model.gguf -f winogrande-debiased-eval.csv --winogrande [--winogrande-tasks N] [other params]"
 echo ""
 
 exit 0
diff --git a/scripts/hf.sh b/scripts/hf.sh
index 58f83d6f..85c2c4d9 100755
--- a/scripts/hf.sh
+++ b/scripts/hf.sh
@@ -3,9 +3,9 @@
 # Shortcut for downloading HF models
 #
 # Usage:
-#   ./main -m $(./scripts/hf.sh https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/resolve/main/mixtral-8x7b-v0.1.Q4_K_M.gguf)
-#   ./main -m $(./scripts/hf.sh --url https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q4_K_M.gguf)
-#   ./main -m $(./scripts/hf.sh --repo TheBloke/Mixtral-8x7B-v0.1-GGUF --file mixtral-8x7b-v0.1.Q4_K_M.gguf)
+#   ./llama-cli -m $(./scripts/hf.sh https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/resolve/main/mixtral-8x7b-v0.1.Q4_K_M.gguf)
+#   ./llama-cli -m $(./scripts/hf.sh --url https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q4_K_M.gguf)
+#   ./llama-cli -m $(./scripts/hf.sh --repo TheBloke/Mixtral-8x7B-v0.1-GGUF --file mixtral-8x7b-v0.1.Q4_K_M.gguf)
 #
 
 # all logs go to stderr
diff --git a/scripts/pod-llama.sh b/scripts/pod-llama.sh
index 5dabbf60..6ba499a2 100644
--- a/scripts/pod-llama.sh
+++ b/scripts/pod-llama.sh
@@ -77,9 +77,9 @@ if [ "$1" -eq "1" ]; then
 
     python3 examples/convert-legacy-llama.py ./models/tinyllama-1b  --outfile ./models/tinyllama-1b/ggml-model-f16.gguf  --outtype f16
 
-    ./quantize ./models/tinyllama-1b/ggml-model-f16.gguf ./models/tinyllama-1b/ggml-model-q4_0.gguf q4_0
-    ./quantize ./models/tinyllama-1b/ggml-model-f16.gguf ./models/tinyllama-1b/ggml-model-q4_k.gguf q4_k
-    ./quantize ./models/tinyllama-1b/ggml-model-f16.gguf ./models/tinyllama-1b/ggml-model-q8_0.gguf q8_0
+    ./llama-quantize ./models/tinyllama-1b/ggml-model-f16.gguf ./models/tinyllama-1b/ggml-model-q4_0.gguf q4_0
+    ./llama-quantize ./models/tinyllama-1b/ggml-model-f16.gguf ./models/tinyllama-1b/ggml-model-q4_k.gguf q4_k
+    ./llama-quantize ./models/tinyllama-1b/ggml-model-f16.gguf ./models/tinyllama-1b/ggml-model-q8_0.gguf q8_0
 fi
 
 if [ "$1" -eq "2" ]; then
@@ -92,9 +92,9 @@ if [ "$1" -eq "2" ]; then
 
     python3 examples/convert-legacy-llama.py ./models/codellama-7b  --outfile ./models/codellama-7b/ggml-model-f16.gguf  --outtype f16
 
-    ./quantize ./models/codellama-7b/ggml-model-f16.gguf ./models/codellama-7b/ggml-model-q4_0.gguf q4_0
-    ./quantize ./models/codellama-7b/ggml-model-f16.gguf ./models/codellama-7b/ggml-model-q4_k.gguf q4_k
-    ./quantize ./models/codellama-7b/ggml-model-f16.gguf ./models/codellama-7b/ggml-model-q8_0.gguf q8_0
+    ./llama-quantize ./models/codellama-7b/ggml-model-f16.gguf ./models/codellama-7b/ggml-model-q4_0.gguf q4_0
+    ./llama-quantize ./models/codellama-7b/ggml-model-f16.gguf ./models/codellama-7b/ggml-model-q4_k.gguf q4_k
+    ./llama-quantize ./models/codellama-7b/ggml-model-f16.gguf ./models/codellama-7b/ggml-model-q8_0.gguf q8_0
 fi
 
 if [ "$1" -eq "3" ]; then
@@ -107,9 +107,9 @@ if [ "$1" -eq "3" ]; then
 
     python3 examples/convert-legacy-llama.py ./models/codellama-13b --outfile ./models/codellama-13b/ggml-model-f16.gguf --outtype f16
 
-    ./quantize ./models/codellama-13b/ggml-model-f16.gguf ./models/codellama-13b/ggml-model-q4_0.gguf q4_0
-    ./quantize ./models/codellama-13b/ggml-model-f16.gguf ./models/codellama-13b/ggml-model-q4_k.gguf q4_k
-    ./quantize ./models/codellama-13b/ggml-model-f16.gguf ./models/codellama-13b/ggml-model-q8_0.gguf q8_0
+    ./llama-quantize ./models/codellama-13b/ggml-model-f16.gguf ./models/codellama-13b/ggml-model-q4_0.gguf q4_0
+    ./llama-quantize ./models/codellama-13b/ggml-model-f16.gguf ./models/codellama-13b/ggml-model-q4_k.gguf q4_k
+    ./llama-quantize ./models/codellama-13b/ggml-model-f16.gguf ./models/codellama-13b/ggml-model-q8_0.gguf q8_0
 fi
 
 if [ "$1" -eq "4" ]; then
@@ -122,9 +122,9 @@ if [ "$1" -eq "4" ]; then
 
     python3 examples/convert-legacy-llama.py ./models/codellama-34b --outfile ./models/codellama-34b/ggml-model-f16.gguf --outtype f16
 
-    ./quantize ./models/codellama-34b/ggml-model-f16.gguf ./models/codellama-34b/ggml-model-q4_0.gguf q4_0
-    ./quantize ./models/codellama-34b/ggml-model-f16.gguf ./models/codellama-34b/ggml-model-q4_k.gguf q4_k
-    ./quantize ./models/codellama-34b/ggml-model-f16.gguf ./models/codellama-34b/ggml-model-q8_0.gguf q8_0
+    ./llama-quantize ./models/codellama-34b/ggml-model-f16.gguf ./models/codellama-34b/ggml-model-q4_0.gguf q4_0
+    ./llama-quantize ./models/codellama-34b/ggml-model-f16.gguf ./models/codellama-34b/ggml-model-q4_k.gguf q4_k
+    ./llama-quantize ./models/codellama-34b/ggml-model-f16.gguf ./models/codellama-34b/ggml-model-q8_0.gguf q8_0
 fi
 
 if [ "$1" -eq "5" ]; then
@@ -137,9 +137,9 @@ if [ "$1" -eq "5" ]; then
 
     python3 examples/convert-legacy-llama.py ./models/codellama-7b-instruct  --outfile ./models/codellama-7b-instruct/ggml-model-f16.gguf  --outtype f16
 
-    ./quantize ./models/codellama-7b-instruct/ggml-model-f16.gguf ./models/codellama-7b-instruct/ggml-model-q4_0.gguf q4_0
-    ./quantize ./models/codellama-7b-instruct/ggml-model-f16.gguf ./models/codellama-7b-instruct/ggml-model-q4_k.gguf q4_k
-    ./quantize ./models/codellama-7b-instruct/ggml-model-f16.gguf ./models/codellama-7b-instruct/ggml-model-q8_0.gguf q8_0
+    ./llama-quantize ./models/codellama-7b-instruct/ggml-model-f16.gguf ./models/codellama-7b-instruct/ggml-model-q4_0.gguf q4_0
+    ./llama-quantize ./models/codellama-7b-instruct/ggml-model-f16.gguf ./models/codellama-7b-instruct/ggml-model-q4_k.gguf q4_k
+    ./llama-quantize ./models/codellama-7b-instruct/ggml-model-f16.gguf ./models/codellama-7b-instruct/ggml-model-q8_0.gguf q8_0
 fi
 
 if [ "$1" -eq "6" ]; then
@@ -152,9 +152,9 @@ if [ "$1" -eq "6" ]; then
 
     python3 examples/convert-legacy-llama.py ./models/codellama-13b-instruct --outfile ./models/codellama-13b-instruct/ggml-model-f16.gguf --outtype f16
 
-    ./quantize ./models/codellama-13b-instruct/ggml-model-f16.gguf ./models/codellama-13b-instruct/ggml-model-q4_0.gguf q4_0
-    ./quantize ./models/codellama-13b-instruct/ggml-model-f16.gguf ./models/codellama-13b-instruct/ggml-model-q4_k.gguf q4_k
-    ./quantize ./models/codellama-13b-instruct/ggml-model-f16.gguf ./models/codellama-13b-instruct/ggml-model-q8_0.gguf q8_0
+    ./llama-quantize ./models/codellama-13b-instruct/ggml-model-f16.gguf ./models/codellama-13b-instruct/ggml-model-q4_0.gguf q4_0
+    ./llama-quantize ./models/codellama-13b-instruct/ggml-model-f16.gguf ./models/codellama-13b-instruct/ggml-model-q4_k.gguf q4_k
+    ./llama-quantize ./models/codellama-13b-instruct/ggml-model-f16.gguf ./models/codellama-13b-instruct/ggml-model-q8_0.gguf q8_0
 fi
 
 if [ "$1" -eq "7" ]; then
@@ -167,9 +167,9 @@ if [ "$1" -eq "7" ]; then
 
     python3 examples/convert-legacy-llama.py ./models/codellama-34b-instruct --outfile ./models/codellama-34b-instruct/ggml-model-f16.gguf --outtype f16
 
-    ./quantize ./models/codellama-34b-instruct/ggml-model-f16.gguf ./models/codellama-34b-instruct/ggml-model-q4_0.gguf q4_0
-    ./quantize ./models/codellama-34b-instruct/ggml-model-f16.gguf ./models/codellama-34b-instruct/ggml-model-q4_k.gguf q4_k
-    ./quantize ./models/codellama-34b-instruct/ggml-model-f16.gguf ./models/codellama-34b-instruct/ggml-model-q8_0.gguf q8_0
+    ./llama-quantize ./models/codellama-34b-instruct/ggml-model-f16.gguf ./models/codellama-34b-instruct/ggml-model-q4_0.gguf q4_0
+    ./llama-quantize ./models/codellama-34b-instruct/ggml-model-f16.gguf ./models/codellama-34b-instruct/ggml-model-q4_k.gguf q4_k
+    ./llama-quantize ./models/codellama-34b-instruct/ggml-model-f16.gguf ./models/codellama-34b-instruct/ggml-model-q8_0.gguf q8_0
 fi
 
 if [ "$1" -eq "1" ]; then
@@ -181,22 +181,22 @@ if [ "$1" -eq "1" ]; then
     ../scripts/get-wikitext-2.sh
     unzip wikitext-2-raw-v1.zip
 
-    make -j && ./bin/perplexity -m ../models/tinyllama-1b/ggml-model-f16.gguf -f ./wikitext-2-raw/wiki.test.raw -ngl 100 --chunks 32
+    make -j && ./bin/llama-perplexity -m ../models/tinyllama-1b/ggml-model-f16.gguf -f ./wikitext-2-raw/wiki.test.raw -ngl 100 --chunks 32
 
     # batched
     cd /workspace/llama.cpp
 
-    LLAMA_CUDA=1 make -j && ./batched ./models/tinyllama-1b/ggml-model-f16.gguf "Hello, my name is" 8 128 999
+    LLAMA_CUDA=1 make -j && ./llama-batched ./models/tinyllama-1b/ggml-model-f16.gguf "Hello, my name is" 8 128 999
 
     # batched-bench
     cd /workspace/llama.cpp
 
-    LLAMA_CUDA=1 make -j && ./batched-bench ./models/tinyllama-1b/ggml-model-f16.gguf 4608 1 99 0 512 128 1,2,3,4,5,6,7,8,16,32
+    LLAMA_CUDA=1 make -j && ./llama-batched-bench ./models/tinyllama-1b/ggml-model-f16.gguf 4608 1 99 0 512 128 1,2,3,4,5,6,7,8,16,32
 
     # parallel
     cd /workspace/llama.cpp
 
-    LLAMA_CUDA=1 make -j && ./parallel -m ./models/tinyllama-1b/ggml-model-f16.gguf -t 1 -ngl 100 -c 4096 -b 512 -s 1 -np 8 -ns 128 -n 100 -cb
+    LLAMA_CUDA=1 make -j && ./llama-parallel -m ./models/tinyllama-1b/ggml-model-f16.gguf -t 1 -ngl 100 -c 4096 -b 512 -s 1 -np 8 -ns 128 -n 100 -cb
 
 fi
 
@@ -204,10 +204,10 @@ fi
 #if [ "$1" -eq "7" ]; then
 #    cd /workspace/llama.cpp
 #
-#    LLAMA_CUDA=1 make -j && ./speculative -m ./models/codellama-34b-instruct/ggml-model-f16.gguf -md ./models/codellama-7b-instruct/ggml-model-q4_0.gguf -p "# Dijkstra's shortest path algorithm in Python (4 spaces indentation) + complexity analysis:\n\n" -e -ngl 999 -ngld 999 -t 4 -n 512 -c 4096 -s 21 --draft 16 -np 1 --temp 0.0
+#    LLAMA_CUDA=1 make -j && ./llama-speculative -m ./models/codellama-34b-instruct/ggml-model-f16.gguf -md ./models/codellama-7b-instruct/ggml-model-q4_0.gguf -p "# Dijkstra's shortest path algorithm in Python (4 spaces indentation) + complexity analysis:\n\n" -e -ngl 999 -ngld 999 -t 4 -n 512 -c 4096 -s 21 --draft 16 -np 1 --temp 0.0
 #fi
 
 # more benches
-#LLAMA_CUDA=1 make -j && ./batched-bench ./models/codellama-7b/ggml-model-q4_k.gguf  4096 1 99 1 512,3200 128,128,800 1
-#LLAMA_CUDA=1 make -j && ./batched-bench ./models/codellama-13b/ggml-model-q4_k.gguf 4096 1 99 1 512,3200 128,128,800 1
+#LLAMA_CUDA=1 make -j && ./llama-batched-bench ./models/codellama-7b/ggml-model-q4_k.gguf  4096 1 99 1 512,3200 128,128,800 1
+#LLAMA_CUDA=1 make -j && ./llama-batched-bench ./models/codellama-13b/ggml-model-q4_k.gguf 4096 1 99 1 512,3200 128,128,800 1
 
diff --git a/scripts/qnt-all.sh b/scripts/qnt-all.sh
index b4c2a159..bc43738a 100755
--- a/scripts/qnt-all.sh
+++ b/scripts/qnt-all.sh
@@ -26,5 +26,5 @@ set -e
 mkdir -p ${out}
 
 for q in ${qnt[@]}; do
-    time ./bin/quantize ../models/${model}/ggml-model-f16.gguf ../models/${model}/ggml-model-${q}.gguf ${q} 2>&1 ${args} | tee ${out}/qnt-${q}.txt
+    time ./bin/llama-quantize ../models/${model}/ggml-model-f16.gguf ../models/${model}/ggml-model-${q}.gguf ${q} 2>&1 ${args} | tee ${out}/qnt-${q}.txt
 done
diff --git a/scripts/run-all-ppl.sh b/scripts/run-all-ppl.sh
index e04d61d7..e15f74f1 100755
--- a/scripts/run-all-ppl.sh
+++ b/scripts/run-all-ppl.sh
@@ -26,5 +26,5 @@ out="../tmp/results-${model}"
 mkdir -p ${out}
 
 for q in ${qnt[@]}; do
-    time ./bin/perplexity -m ../models/${model}/ggml-model-f16.gguf -f ./wiki.test.raw ${args} 2>&1 | tee ${out}/ppl-${q}.txt
+    time ./bin/llama-perplexity -m ../models/${model}/ggml-model-f16.gguf -f ./wiki.test.raw ${args} 2>&1 | tee ${out}/ppl-${q}.txt
 done
diff --git a/scripts/run-with-preset.py b/scripts/run-with-preset.py
index 0d721911..ee21eab3 100755
--- a/scripts/run-with-preset.py
+++ b/scripts/run-with-preset.py
@@ -10,7 +10,7 @@ import yaml
 
 logger = logging.getLogger("run-with-preset")
 
-CLI_ARGS_MAIN_PERPLEXITY = [
+CLI_ARGS_LLAMA_CLI_PERPLEXITY = [
     "batch-size", "cfg-negative-prompt", "cfg-scale", "chunks", "color", "ctx-size", "escape",
     "export", "file", "frequency-penalty", "grammar", "grammar-file", "hellaswag",
     "hellaswag-tasks", "ignore-eos", "in-prefix", "in-prefix-bos", "in-suffix",
@@ -29,7 +29,7 @@ CLI_ARGS_LLAMA_BENCH = [
     "n-prompt", "output", "repetitions", "tensor-split", "threads", "verbose"
 ]
 
-CLI_ARGS_SERVER = [
+CLI_ARGS_LLAMA_SERVER = [
     "alias", "batch-size", "ctx-size", "embedding", "host", "memory-f32", "lora", "lora-base",
     "low-vram", "main-gpu", "mlock", "model", "n-gpu-layers", "n-probs", "no-mmap", "no-mul-mat-q",
     "numa", "path", "port", "rope-freq-base", "timeout", "rope-freq-scale", "tensor-split",
@@ -37,7 +37,7 @@ CLI_ARGS_SERVER = [
 ]
 
 description = """Run llama.cpp binaries with presets from YAML file(s).
-To specify which binary should be run, specify the "binary" property (main, perplexity, llama-bench, and server are supported).
+To specify which binary should be run, specify the "binary" property (llama-cli, llama-perplexity, llama-bench, and llama-server are supported).
 To get a preset file template, run a llama.cpp binary with the "--logdir" CLI argument.
 
 Formatting considerations:
@@ -77,19 +77,19 @@ for yaml_file in known_args.yaml_files:
 
 props = {prop.replace("_", "-"): val for prop, val in props.items()}
 
-binary = props.pop("binary", "main")
+binary = props.pop("binary", "llama-cli")
 if known_args.binary:
     binary = known_args.binary
 
 if os.path.exists(f"./{binary}"):
     binary = f"./{binary}"
 
-if binary.lower().endswith("main") or binary.lower().endswith("perplexity"):
-    cli_args = CLI_ARGS_MAIN_PERPLEXITY
+if binary.lower().endswith("llama-cli") or binary.lower().endswith("llama-perplexity"):
+    cli_args = CLI_ARGS_LLAMA_CLI_PERPLEXITY
 elif binary.lower().endswith("llama-bench"):
     cli_args = CLI_ARGS_LLAMA_BENCH
-elif binary.lower().endswith("server"):
-    cli_args = CLI_ARGS_SERVER
+elif binary.lower().endswith("llama-server"):
+    cli_args = CLI_ARGS_LLAMA_SERVER
 else:
     logger.error(f"Unknown binary: {binary}")
     sys.exit(1)
diff --git a/scripts/server-llm.sh b/scripts/server-llm.sh
index b3715e20..19923244 100644
--- a/scripts/server-llm.sh
+++ b/scripts/server-llm.sh
@@ -380,13 +380,13 @@ fi
 
 if [[ "$backend" == "cuda" ]]; then
     printf "[+] Building with CUDA backend\n"
-    LLAMA_CUDA=1 make -j server $log
+    LLAMA_CUDA=1 make -j llama-server $log
 elif [[ "$backend" == "cpu" ]]; then
     printf "[+] Building with CPU backend\n"
-    make -j server $log
+    make -j llama-server $log
 elif [[ "$backend" == "metal" ]]; then
     printf "[+] Building with Metal backend\n"
-    make -j server $log
+    make -j llama-server $log
 else
     printf "[-] Unknown backend: %s\n" "$backend"
     exit 1
@@ -413,6 +413,6 @@ if [[ $verbose -eq 1 ]]; then
     args="$args --verbose"
 fi
 
-./server -m "../$wfile" --host 0.0.0.0 --port "$port" -c $n_kv -np "$n_parallel" $args
+./llama-server -m "../$wfile" --host 0.0.0.0 --port "$port" -c $n_kv -np "$n_parallel" $args
 
 exit 0