From 42d5fc198668149ab0ed2c71920849ef0150cf3b Mon Sep 17 00:00:00 2001 From: Xuan Son Nguyen Date: Mon, 9 Sep 2024 20:25:53 +0200 Subject: [PATCH] update server readme --- examples/gen-docs/gen-docs.cpp | 2 +- examples/server/README.md | 19 +++++++------------ 2 files changed, 8 insertions(+), 13 deletions(-) diff --git a/examples/gen-docs/gen-docs.cpp b/examples/gen-docs/gen-docs.cpp index 640ee7184..b6d4725fd 100644 --- a/examples/gen-docs/gen-docs.cpp +++ b/examples/gen-docs/gen-docs.cpp @@ -10,7 +10,7 @@ static void export_md(std::string fname, llama_example ex) { std::ofstream file(fname, std::ofstream::out | std::ofstream::trunc); gpt_params params; - if (!gpt_params_parse(argc, argv, params, ex)) { + auto ctx_arg = gpt_params_parser_init(params, ex); file << "| Argument | Explanation |\n"; file << "| -------- | ----------- |\n"; diff --git a/examples/server/README.md b/examples/server/README.md index ed1201ba8..79196e9c1 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -23,36 +23,32 @@ The project is under active development, and we are [looking for feedback and co | `--version` | show version and build info | | `-v, --verbose` | print verbose information | | `--verbosity N` | set specific verbosity level (default: 0) | -| `--verbose-prompt` | print a verbose prompt before generation (default: false) | -| `--no-display-prompt` | don't print prompt at generation (default: false) | -| `-s, --seed SEED` | RNG seed (default: -1, use random seed for < 0) | | `-t, --threads N` | number of threads to use during generation (default: -1)
(env: LLAMA_ARG_THREADS) | | `-tb, --threads-batch N` | number of threads to use during batch and prompt processing (default: same as --threads) | | `-C, --cpu-mask M` | CPU affinity mask: arbitrarily long hex. Complements cpu-range (default: "") | | `-Cr, --cpu-range lo-hi` | range of CPUs for affinity. Complements --cpu-mask | | `--cpu-strict <0\|1>` | use strict CPU placement (default: 0)
| +| `--prio N` | set process/thread priority : 0-normal, 1-medium, 2-high, 3-realtime (default: 0)
| | `--poll <0...100>` | use polling level to wait for work (0 - no polling, default: 50)
| | `-Cb, --cpu-mask-batch M` | CPU affinity mask: arbitrarily long hex. Complements cpu-range-batch (default: same as --cpu-mask) | | `-Crb, --cpu-range-batch lo-hi` | ranges of CPUs for affinity. Complements --cpu-mask-batch | | `--cpu-strict-batch <0\|1>` | use strict CPU placement (default: same as --cpu-strict) | +| `--prio-batch N` | set process/thread priority : 0-normal, 1-medium, 2-high, 3-realtime (default: 0)
| | `--poll-batch <0\|1>` | use polling to wait for work (default: same as --poll) | -| `-lcs, --lookup-cache-static FNAME` | path to static lookup cache to use for lookup decoding (not updated by generation) | -| `-lcd, --lookup-cache-dynamic FNAME` | path to dynamic lookup cache to use for lookup decoding (updated by generation) | | `-c, --ctx-size N` | size of the prompt context (default: 0, 0 = loaded from model)
(env: LLAMA_ARG_CTX_SIZE) | | `-n, --predict, --n-predict N` | number of tokens to predict (default: -1, -1 = infinity, -2 = until context filled)
(env: LLAMA_ARG_N_PREDICT) | | `-b, --batch-size N` | logical maximum batch size (default: 2048)
(env: LLAMA_ARG_BATCH) | | `-ub, --ubatch-size N` | physical maximum batch size (default: 512)
(env: LLAMA_ARG_UBATCH) | | `--keep N` | number of tokens to keep from the initial prompt (default: 0, -1 = all) | -| `--chunks N` | max number of chunks to process (default: -1, -1 = all) | | `-fa, --flash-attn` | enable Flash Attention (default: disabled)
(env: LLAMA_ARG_FLASH_ATTN) | | `-p, --prompt PROMPT` | prompt to start generation with | | `-f, --file FNAME` | a file containing the prompt (default: none) | -| `--in-file FNAME` | an input file (repeat to specify multiple files) | | `-bf, --binary-file FNAME` | binary file containing the prompt (default: none) | | `-e, --escape` | process escapes sequences (\n, \r, \t, \', \", \\) (default: true) | | `--no-escape` | do not process escape sequences | | `--spm-infill` | use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this. (default: disabled) | -| `--samplers SAMPLERS` | samplers that will be used for generation in the order, separated by ';'
(default: top_k;tfs_z;typical_p;top_p;min_p;temperature) | +| `--samplers SAMPLERS` | samplers that will be used for generation in the order, separated by ';'
(default: top_k;tfs_z;typ_p;top_p;min_p;temperature) | +| `-s, --seed SEED` | RNG seed (default: -1, use random seed for < 0) | | `--sampling-seq SEQUENCE` | simplified sequence for samplers that will be used (default: kfypmt) | | `--ignore-eos` | ignore end of stream token and continue generating (implies --logit-bias EOS-inf) | | `--penalize-nl` | penalize newline tokens (default: false) | @@ -92,13 +88,12 @@ The project is under active development, and we are [looking for feedback and co | `-ctv, --cache-type-v TYPE` | KV cache data type for V (default: f16) | | `-dt, --defrag-thold N` | KV cache defragmentation threshold (default: -1.0, < 0 - disabled)
(env: LLAMA_ARG_DEFRAG_THOLD) | | `-np, --parallel N` | number of parallel sequences to decode (default: 1) | -| `-ns, --sequences N` | number of sequences to decode (default: 1) | | `-cb, --cont-batching` | enable continuous batching (a.k.a dynamic batching) (default: enabled)
(env: LLAMA_ARG_CONT_BATCHING) | | `-nocb, --no-cont-batching` | disable continuous batching
(env: LLAMA_ARG_NO_CONT_BATCHING) | | `--mlock` | force system to keep model in RAM rather than swapping or compressing | | `--no-mmap` | do not memory-map model (slower load but may reduce pageouts if not using mlock) | | `--numa TYPE` | attempt optimizations that help on some NUMA systems
- distribute: spread execution evenly over all nodes
- isolate: only spawn threads on CPUs on the node that execution started on
- numactl: use the CPU map provided by numactl
if run without this previously, it is recommended to drop the system page cache before using this
see https://github.com/ggerganov/llama.cpp/issues/1437 | -| `-ngl, --gpu-layers N` | number of layers to store in VRAM
(env: LLAMA_ARG_N_GPU_LAYERS) | +| `-ngl, --gpu-layers, --n-gpu-layers N` | number of layers to store in VRAM
(env: LLAMA_ARG_N_GPU_LAYERS) | | `-sm, --split-mode {none,layer,row}` | how to split the model across multiple GPUs, one of:
- none: use one GPU only
- layer (default): split layers and KV across GPUs
- row: split rows across GPUs | | `-ts, --tensor-split N0,N1,N2,...` | fraction of the model to offload to each GPU, comma-separated list of proportions, e.g. 3,1 | | `-mg, --main-gpu INDEX` | the GPU to use for the model (with split-mode = none), or for intermediate results and KV (with split-mode = row) (default: 0) | @@ -109,7 +104,7 @@ The project is under active development, and we are [looking for feedback and co | `--control-vector FNAME` | add a control vector
note: this argument can be repeated to add multiple control vectors | | `--control-vector-scaled FNAME SCALE` | add a control vector with user defined scaling SCALE
note: this argument can be repeated to add multiple scaled control vectors | | `--control-vector-layer-range START END` | layer range to apply the control vector(s) to, start and end inclusive | -| `-a, --alias STRING` | set alias for model name (to be used by REST API)
(env: LLAMA_ARG_MODEL) | +| `-a, --alias STRING` | set alias for model name (to be used by REST API) | | `-m, --model FNAME` | model path (default: `models/$filename` with filename from `--hf-file` or `--model-url` if set, otherwise models/7B/ggml-model-f16.gguf)
(env: LLAMA_ARG_MODEL) | | `-mu, --model-url MODEL_URL` | model download url (default: unused)
(env: LLAMA_ARG_MODEL_URL) | | `-hfr, --hf-repo REPO` | Hugging Face model repository (default: unused)
(env: LLAMA_ARG_HF_REPO) | @@ -123,7 +118,7 @@ The project is under active development, and we are [looking for feedback and co | `--api-key-file FNAME` | path to file containing API keys (default: none) | | `--ssl-key-file FNAME` | path to file a PEM-encoded SSL private key | | `--ssl-cert-file FNAME` | path to file a PEM-encoded SSL certificate | -| `--timeout N` | server read/write timeout in seconds (default: 600) | +| `-to, --timeout N` | server read/write timeout in seconds (default: 600) | | `--threads-http N` | number of threads used to process HTTP requests (default: -1)
(env: LLAMA_ARG_THREADS_HTTP) | | `-spf, --system-prompt-file FNAME` | set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications | | `--log-format {text, json}` | log output format: json or text (default: json) |