From 6b3696013c20a3bfde0156373f77a57e13eec163 Mon Sep 17 00:00:00 2001 From: Xuan Son Nguyen Date: Thu, 12 Dec 2024 21:14:45 +0100 Subject: [PATCH] regenerate docs --- examples/CMakeLists.txt | 1 + examples/server/README.md | 19 ++++++++++--------- 2 files changed, 11 insertions(+), 9 deletions(-) diff --git a/examples/CMakeLists.txt b/examples/CMakeLists.txt index b2df4f2fb..21b31392e 100644 --- a/examples/CMakeLists.txt +++ b/examples/CMakeLists.txt @@ -51,6 +51,7 @@ else() add_subdirectory(speculative) add_subdirectory(speculative-simple) add_subdirectory(tokenize) + add_subdirectory(gen-docs) if (NOT GGML_BACKEND_DL) # these examples use the backends directly and cannot be built with dynamic loading add_subdirectory(convert-llama2c-to-ggml) diff --git a/examples/server/README.md b/examples/server/README.md index 686be7baf..a9443e56b 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -62,8 +62,8 @@ The project is under active development, and we are [looking for feedback and co | `--yarn-beta-fast N` | YaRN: low correction dim or beta (default: 32.0)
(env: LLAMA_ARG_YARN_BETA_FAST) | | `-dkvc, --dump-kv-cache` | verbose print of the KV cache | | `-nkvo, --no-kv-offload` | disable KV offload
(env: LLAMA_ARG_NO_KV_OFFLOAD) | -| `-ctk, --cache-type-k TYPE` | KV cache data type for K (default: f16)
(env: LLAMA_ARG_CACHE_TYPE_K) | -| `-ctv, --cache-type-v TYPE` | KV cache data type for V (default: f16)
(env: LLAMA_ARG_CACHE_TYPE_V) | +| `-ctk, --cache-type-k TYPE` | KV cache data type for K
allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1
(default: f16)
(env: LLAMA_ARG_CACHE_TYPE_K) | +| `-ctv, --cache-type-v TYPE` | KV cache data type for V
allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1
(default: f16)
(env: LLAMA_ARG_CACHE_TYPE_V) | | `-dt, --defrag-thold N` | KV cache defragmentation threshold (default: 0.1, < 0 - disabled)
(env: LLAMA_ARG_DEFRAG_THOLD) | | `-np, --parallel N` | number of parallel sequences to decode (default: 1)
(env: LLAMA_ARG_N_PARALLEL) | | `--mlock` | force system to keep model in RAM rather than swapping or compressing
(env: LLAMA_ARG_MLOCK) | @@ -138,6 +138,7 @@ The project is under active development, and we are [looking for feedback and co | -------- | ----------- | | `--no-context-shift` | disables context shift on inifinite text generation (default: disabled)
(env: LLAMA_ARG_NO_CONTEXT_SHIFT) | | `-sp, --special` | special tokens output enabled (default: false) | +| `--no-warmup` | skip warming up the model with an empty run | | `--spm-infill` | use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this. (default: disabled) | | `--pooling {none,mean,cls,last,rank}` | pooling type for embeddings, use model default if unspecified
(env: LLAMA_ARG_POOLING) | | `-cb, --cont-batching` | enable continuous batching (a.k.a dynamic batching) (default: enabled)
(env: LLAMA_ARG_CONT_BATCHING) | @@ -146,7 +147,7 @@ The project is under active development, and we are [looking for feedback and co | `--host HOST` | ip address to listen (default: 127.0.0.1)
(env: LLAMA_ARG_HOST) | | `--port PORT` | port to listen (default: 8080)
(env: LLAMA_ARG_PORT) | | `--path PATH` | path to serve static files from (default: )
(env: LLAMA_ARG_STATIC_PATH) | -| `--no-webui` | disable the Web UI
(env: LLAMA_ARG_NO_WEBUI) | +| `--no-webui` | Disable the Web UI (default: enabled)
(env: LLAMA_ARG_NO_WEBUI) | | `--embedding, --embeddings` | restrict to only support embedding use case; use only with dedicated embedding models (default: disabled)
(env: LLAMA_ARG_EMBEDDINGS) | | `--reranking, --rerank` | enable reranking endpoint on server (default: disabled)
(env: LLAMA_ARG_RERANKING) | | `--api-key KEY` | API key to use for authentication (default: none)
(env: LLAMA_API_KEY) | @@ -164,13 +165,13 @@ The project is under active development, and we are [looking for feedback and co | `--chat-template JINJA_TEMPLATE` | set custom jinja chat template (default: template taken from model's metadata)
if suffix/prefix are specified, template will be disabled
list of built-in templates:
chatglm3, chatglm4, chatml, command-r, deepseek, deepseek2, exaone3, gemma, granite, llama2, llama2-sys, llama2-sys-bos, llama2-sys-strip, llama3, minicpm, mistral-v1, mistral-v3, mistral-v3-tekken, mistral-v7, monarch, openchat, orion, phi3, rwkv-world, vicuna, vicuna-orca, zephyr
(env: LLAMA_ARG_CHAT_TEMPLATE) | | `-sps, --slot-prompt-similarity SIMILARITY` | how much the prompt of a request must match the prompt of a slot in order to use that slot (default: 0.50, 0.0 = disabled)
| | `--lora-init-without-apply` | load LoRA adapters without applying them (apply later via POST /lora-adapters) (default: disabled) | -| `--draft-max, --draft, --draft-n N` | number of tokens to draft for speculative decoding (default: 16) | -| `--draft-min, --draft-n-min N` | minimum number of draft tokens to use for speculative decoding (default: 5) | -| `--draft-p-min P` | minimum speculative decoding probability (greedy) (default: 0.9) | -| `-cd, --ctx-size-draft N` | size of the prompt context for the draft model (default: 0, 0 = loaded from model) | +| `--draft-max, --draft, --draft-n N` | number of tokens to draft for speculative decoding (default: 16)
(env: LLAMA_ARG_DRAFT_MAX) | +| `--draft-min, --draft-n-min N` | minimum number of draft tokens to use for speculative decoding (default: 5)
(env: LLAMA_ARG_DRAFT_MIN) | +| `--draft-p-min P` | minimum speculative decoding probability (greedy) (default: 0.9)
(env: LLAMA_ARG_DRAFT_P_MIN) | +| `-cd, --ctx-size-draft N` | size of the prompt context for the draft model (default: 0, 0 = loaded from model)
(env: LLAMA_ARG_CTX_SIZE_DRAFT) | | `-devd, --device-draft ` | comma-separated list of devices to use for offloading the draft model (none = don't offload)
use --list-devices to see a list of available devices | -| `-ngld, --gpu-layers-draft, --n-gpu-layers-draft N` | number of layers to store in VRAM for the draft model | -| `-md, --model-draft FNAME` | draft model for speculative decoding (default: unused) | +| `-ngld, --gpu-layers-draft, --n-gpu-layers-draft N` | number of layers to store in VRAM for the draft model
(env: LLAMA_ARG_N_GPU_LAYERS_DRAFT) | +| `-md, --model-draft FNAME` | draft model for speculative decoding (default: unused)
(env: LLAMA_ARG_MODEL_DRAFT) | Note: If both command line argument and environment variable are both set for the same param, the argument will take precedence over env var.