owen/longhaul.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

stuff

Browse Source
This commit is contained in:
Owen Qwen
2026-07-29 17:17:25 -05:00
parent fdd9fcf85e
commit a673afad85
17 changed files with 1071 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/README.md
+8 -2
View File
@@ -53,6 +53,9 @@ For the full list of features, please refer to [server's changelog](https://gith
| `-ub, --ubatch-size N` | physical maximum batch size (default: 512)<br/>(env: LLAMA_ARG_UBATCH) |
| `--keep N` | number of tokens to keep from the initial prompt (default: 0, -1 = all) |
| `--swa-full` | use full-size SWA cache (default: false)<br/>[(more info)](https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)<br/>(env: LLAMA_ARG_SWA_FULL) |
| `--token-cache-size N` | shared tokenizer and tokenized-text cache size in MiB (default: 5120, 0 = disable)<br/>(env: LLAMA_ARG_TOKEN_CACHE_SIZE) |
| `--token-cache-dir PATH` | path to the shared tokenizer and tokenized-text cache database<br/>(env: LLAMA_ARG_TOKEN_CACHE_DIR) |
| `--token-cache-clear` | clear the shared tokenizer and tokenized-text cache before loading the model<br/>(env: LLAMA_ARG_TOKEN_CACHE_CLEAR) |
| `-fa, --flash-attn [on\|off\|auto]` | set Flash Attention use ('on', 'off', or 'auto', default: 'auto')<br/>(env: LLAMA_ARG_FLASH_ATTN) |
| `--perf, --no-perf` | whether to enable internal libllama performance timings (default: false)<br/>(env: LLAMA_ARG_PERF) |
| `-e, --escape, --no-escape` | whether to process escapes sequences (\n, \r, \t, \', \", \\) (default: true) |
@@ -71,11 +74,12 @@ For the full list of features, please refer to [server's changelog](https://gith
| `-ctk, --cache-type-k TYPE` | KV cache data type for K<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_K) |
| `-ctv, --cache-type-v TYPE` | KV cache data type for V<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
| `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
| `--rpc SERVERS` | comma-separated list of RPC servers (host:port)<br/>(env: LLAMA_ARG_RPC) |
| `--mlock` | DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
| `--mmap, --no-mmap` | DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_MMAP) |
| `-dio, --direct-io, -ndio, --no-direct-io` | DEPRECATED in favor of `--load-mode`: use DirectIO if available<br/>(env: LLAMA_ARG_DIO) |
| `-lm, --load-mode MODE` | model loading mode (default: mmap)<br/>- none: no special loading mode<br/>- mmap: memory-map model (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>- mlock: force system to keep model in RAM rather than swapping or compressing<br/>- mmap+mlock: mmap + force system to keep model in RAM rather than swapping or compressing<br/>- dio: use DirectIO if available<br/><br/>(env: LLAMA_ARG_LOAD_MODE) |
| `-lm, --load-mode MODE` | model loading mode (default: mmap)<br/>- none: no special loading mode<br/>- mmap: memory-map model (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>- mlock: force system to keep model in RAM rather than swapping or compressing<br/>- mmap+mlock: mmap + force system to keep model in RAM rather than swapping or compressing<br/>- dio: use DirectIO if available<br/>- longhaul: stream routed MoE experts through a bounded cache<br/><br/>(env: LLAMA_ARG_LOAD_MODE) |
| `--longhaul` | stream routed Qwen3.5 MoE experts through a bounded Metal cache<br/>(env: LLAMA_ARG_LONGHAUL) |
| `--longhaul-cache N` | longhaul expert cache size in GiB<br/>(env: LLAMA_ARG_LONGHAUL_CACHE) |
| `--numa TYPE` | attempt optimizations that help on some NUMA systems<br/>- distribute: spread execution evenly over all nodes<br/>- isolate: only spawn threads on CPUs on the node that execution started on<br/>- numactl: use the CPU map provided by numactl<br/>if run without this previously, it is recommended to drop the system page cache before using this<br/>see https://github.com/ggml-org/llama.cpp/issues/1437<br/>(env: LLAMA_ARG_NUMA) |
| `-dev, --device <dev1,dev2,..>` | comma-separated list of devices to use for offloading (none = don't offload)<br/>use --list-devices to see a list of available devices<br/>(env: LLAMA_ARG_DEVICE) |
| `--list-devices` | print list of available devices and exit |
@@ -199,6 +203,8 @@ For the full list of features, please refer to [server's changelog](https://gith
| `--ui-config-file, --webui-config-file PATH` | JSON file that provides default UI settings (overrides UI defaults)<br/>(env: LLAMA_ARG_UI_CONFIG_FILE) |
| `--ui-mcp-proxy, --webui-mcp-proxy, --no-ui-mcp-proxy, --no-webui-mcp-proxy` | experimental: whether to enable MCP CORS proxy - do not enable in untrusted environments (default: disabled)<br/>(env: LLAMA_ARG_UI_MCP_PROXY) |
| `--tools TOOL1,TOOL2,...` | experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)<br/>specify "all" to enable all tools<br/>available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_TOOLS) |
| `--mcp-servers-config PATH` | experimental: path to JSON file with MCP server definitions (Cursor-compatible format) - do not enable in untrusted environments (default: none)<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_MCP_SERVERS_CONFIG) |
| `--mcp-servers-json JSON` | experimental: inline JSON with MCP server definitions (Cursor-compatible format) - do not enable in untrusted environments (default: none)<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_MCP_SERVERS_JSON) |
| `-ag, --agent, -no-ag, --no-agent` | whether to enable CORS proxy and all built-in tools - do not enable in untrusted environments (default: disabled)<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_AGENT) |
| `--ui, --webui, --no-ui, --no-webui` | whether to enable the Web UI (default: enabled)<br/>(env: LLAMA_ARG_UI) |
| `--embedding, --embeddings` | restrict to only support embedding use case; use only with dedicated embedding models (default: disabled)<br/>(env: LLAMA_ARG_EMBEDDINGS) |
tools/server/server-context.cpp
+11 -4
View File
@@ -38,6 +38,7 @@
using json = nlohmann::ordered_json;
constexpr int HTTP_POLLING_SECONDS = 1;
constexpr int64_t PROMPT_TIMING_LOG_INTERVAL_US = 5*1000*1000;
static uint32_t server_n_outputs_max(const common_params & params) {
const uint32_t n_batch = params.n_batch;
@@ -276,6 +277,7 @@ struct server_slot {
// TODO @ngxson : move all metrics to a sub-struct for clarity
int64_t t_start_process_prompt;
int64_t t_start_generation;
int64_t t_prompt_print_last = 0;
int64_t t_print_last = 0;
int32_t n_decoded_last = 0;
@@ -569,13 +571,17 @@ struct server_slot {
SLT_INF(*this, "n_decoded = %6d, tg = %6.2f t/s, tg_3s = %6.2f t/s\n", n_decoded, n_gen_second, n_gen_second_win);
}
void print_timings_pp() const {
void print_timings_pp() {
const int64_t t_now = ggml_time_us();
if (t_now - t_prompt_print_last < PROMPT_TIMING_LOG_INTERVAL_US) {
return;
}
const double n_prompt_second = 1e3 / t_prompt_processing * n_prompt_tokens_processed;
const double f_progress = (float) prompt.n_tokens() / task->n_tokens();
if (t_prompt_processing < 3000.0) {
return;
}
t_prompt_print_last = t_now;
SLT_INF(*this, "prompt processing, n_tokens = %6d, progress = %.2f, t = %6.2f s / %.2f tokens per second\n",
n_prompt_tokens_processed, f_progress, t_prompt_processing / 1e3, n_prompt_second);
@@ -3072,6 +3078,7 @@ private:
// TODO: maybe move branch to outside of this loop in the future
if (slot.state == SLOT_STATE_STARTED) {
slot.t_start_process_prompt = ggml_time_us();
slot.t_prompt_print_last = slot.t_start_process_prompt;
slot.t_start_generation = 0;
slot.state = SLOT_STATE_PROCESSING_PROMPT;