vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

readme : remove --memory-f32 references (#9925)

Browse source
This commit is contained in:
Georgi Gerganov 2024-10-17 23:43:05 +03:00
parent 9f45fc1e99
commit 17bb928080
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
2 changed files with 3 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

6
scripts/run-with-preset.py
View file

@ -15,7 +15,7 @@ CLI_ARGS_LLAMA_CLI_PERPLEXITY = [
"export", "file", "frequency-penalty", "grammar", "grammar-file", "hellaswag",
"hellaswag-tasks", "ignore-eos", "in-prefix", "in-prefix-bos", "in-suffix",
"interactive", "interactive-first", "keep", "logdir", "logit-bias", "lora", "lora-base",
"low-vram", "main-gpu", "memory-f32", "mirostat", "mirostat-ent", "mirostat-lr", "mlock",
"low-vram", "main-gpu", "mirostat", "mirostat-ent", "mirostat-lr", "mlock",
"model", "multiline-input", "n-gpu-layers", "n-predict", "no-mmap", "no-mul-mat-q",
"np-penalize-nl", "numa", "ppl-output-type", "ppl-stride", "presence-penalty", "prompt",
"prompt-cache", "prompt-cache-all", "prompt-cache-ro", "repeat-last-n",
@ -25,12 +25,12 @@ CLI_ARGS_LLAMA_CLI_PERPLEXITY = [
]
CLI_ARGS_LLAMA_BENCH = [
"batch-size", "memory-f32", "low-vram", "model", "mul-mat-q", "n-gen", "n-gpu-layers",
"batch-size", "low-vram", "model", "mul-mat-q", "n-gen", "n-gpu-layers",
"n-prompt", "output", "repetitions", "tensor-split", "threads", "verbose"
]
CLI_ARGS_LLAMA_SERVER = [
"alias", "batch-size", "ctx-size", "embedding", "host", "memory-f32", "lora", "lora-base",
"alias", "batch-size", "ctx-size", "embedding", "host", "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",
"threads", "verbose"