env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-llguidance:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
android:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
macos-latest-arm64:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
# TODO: this build is disabled to save Github Actions resources (https://github.com/ggml-org/llama.cpp/pull/23705)
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
windows-msys2:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-openvino:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-cpu-riscv64-native:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ctest:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ggml-ci-nvidia-cuda:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-vulkan-llvmpipe:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
macos-latest-webgpu:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
build-cmake-pkg:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-22-hip-quality-check:
]
env:
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
- LLAMA_LOG_VERBOSITY: 10
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
]
env:
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
- LLAMA_LOG_VERBOSITY: 10
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
]
env:
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
- LLAMA_LOG_VERBOSITY: 10
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
]
env:
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
- LLAMA_LOG_VERBOSITY: 10
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
]
env:
- LLAMA_LOG_COLORS: 1
- LLAMA_LOG_PREFIX: 1
- LLAMA_LOG_TIMESTAMPS: 1
- LLAMA_LOG_VERBOSITY: 10
+ LLAMA_ARG_LOG_COLORS: 1
+ LLAMA_ARG_LOG_PREFIX: 1
+ LLAMA_ARG_LOG_TIMESTAMPS: 1
+ LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
## main
-export LLAMA_LOG_PREFIX=1
-export LLAMA_LOG_TIMESTAMPS=1
+export LLAMA_ARG_LOG_PREFIX=1
+export LLAMA_ARG_LOG_TIMESTAMPS=1
if [ -z ${GG_BUILD_LOW_PERF} ]; then
# Create symlink: ./llama.cpp/models-mnt -> $MNT/models
params.default_template_kwargs[item.key()] = item.value().dump();
}
}
- ).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_CHAT_TEMPLATE_KWARGS"));
+ ).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_CHAT_TEMPLATE_KWARGS"));
add_opt(common_arg(
{"-to", "--timeout"}, "N",
string_format("server read/write timeout in seconds (default: %d)", params.timeout_read),
[](common_params &, const std::string & value) {
common_log_set_file(common_log_main(), value.c_str());
}
- ).set_env("LLAMA_LOG_FILE"));
+ ).set_env("LLAMA_ARG_LOG_FILE"));
add_opt(common_arg(
{"--log-colors"}, "[on|off|auto]",
"Set colored logging ('on', 'off', or 'auto', default: 'auto')\n"
string_format("error: unknown value for --log-colors: '%s'\n", value.c_str()));
}
}
- ).set_env("LLAMA_LOG_COLORS"));
+ ).set_env("LLAMA_ARG_LOG_COLORS"));
add_opt(common_arg(
{"-v", "--verbose", "--log-verbose"},
"Set verbosity level to infinity (i.e. log all messages, useful for debugging)",
[](common_params & params) {
params.offline = true;
}
- ).set_env("LLAMA_OFFLINE"));
+ ).set_env("LLAMA_ARG_OFFLINE"));
add_opt(common_arg(
{"-lv", "--verbosity", "--log-verbosity"}, "N",
string_format("Set the verbosity threshold. Messages with a higher verbosity will be ignored. Values:\n"
params.verbosity = value;
common_log_set_verbosity_thold(value);
}
- ).set_env("LLAMA_LOG_VERBOSITY"));
+ ).set_env("LLAMA_ARG_LOG_VERBOSITY"));
add_opt(common_arg(
{"--log-prefix"},
{"--no-log-prefix"},
- Usage: `./bin/llama-template-analysis path/to/template.jinja`
-**Debug Logging**: Enable with `LLAMA_LOG_VERBOSITY=2`
+**Debug Logging**: Enable with `LLAMA_ARG_LOG_VERBOSITY=2`
- Shows detailed analysis steps, pattern extraction results, and generated parser structure
| `-hffv, --hf-file-v FILE` | Hugging Face model file for the vocoder model (default: unused)<br/>(env: LLAMA_ARG_HF_FILE_V) |
| `-hft, --hf-token TOKEN` | Hugging Face access token (default: value from HF_TOKEN environment variable)<br/>(env: HF_TOKEN) |
| `--log-disable` | Log disable |
-| `--log-file FNAME` | Log to file<br/>(env: LLAMA_LOG_FILE) |
-| `--log-colors [on\|off\|auto]` | Set colored logging ('on', 'off', or 'auto', default: 'auto')<br/>'auto' enables colors when output is to a terminal<br/>(env: LLAMA_LOG_COLORS) |
+| `--log-file FNAME` | Log to file<br/>(env: LLAMA_ARG_LOG_FILE) |
+| `--log-colors [on\|off\|auto]` | Set colored logging ('on', 'off', or 'auto', default: 'auto')<br/>'auto' enables colors when output is to a terminal<br/>(env: LLAMA_ARG_LOG_COLORS) |
| `-v, --verbose, --log-verbose` | Set verbosity level to infinity (i.e. log all messages, useful for debugging) |
-| `--offline` | Offline mode: forces use of cache, prevents network access<br/>(env: LLAMA_OFFLINE) |
-| `-lv, --verbosity, --log-verbosity N` | Set the verbosity threshold. Messages with a higher verbosity will be ignored. Values:<br/> - 0: generic output<br/> - 1: error<br/> - 2: warning<br/> - 3: info<br/> - 4: debug<br/>(default: 3)<br/><br/>(env: LLAMA_LOG_VERBOSITY) |
+| `--offline` | Offline mode: forces use of cache, prevents network access<br/>(env: LLAMA_ARG_OFFLINE) |
+| `-lv, --verbosity, --log-verbosity N` | Set the verbosity threshold. Messages with a higher verbosity will be ignored. Values:<br/> - 0: generic output<br/> - 1: error<br/> - 2: warning<br/> - 3: info<br/> - 4: trace (more info)<br/> - 5: debug<br/>(default: 3)<br/><br/>(env: LLAMA_ARG_LOG_VERBOSITY) |
| `--log-prefix, --no-log-prefix` | Enable prefix in log messages<br/>(env: LLAMA_ARG_LOG_PREFIX) |
| `--log-timestamps, --no-log-timestamps` | Enable timestamps in log messages<br/>(env: LLAMA_ARG_LOG_TIMESTAMPS) |
| `--spec-draft-type-k, -ctkd, --cache-type-k-draft TYPE` | KV cache data type for K for the draft model<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_SPEC_DRAFT_CACHE_TYPE_K) |
| `--image, --audio FILE` | path to an image or audio file. use with multimodal models, use comma-separated values for multiple files |
| `--image-min-tokens N` | minimum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MIN_TOKENS) |
| `--image-max-tokens N` | maximum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MAX_TOKENS) |
-| `--chat-template-kwargs STRING` | sets additional params for the json template parser, must be a valid json object string, e.g. '{"key1":"value1","key2":"value2"}'<br/>(env: LLAMA_CHAT_TEMPLATE_KWARGS) |
+| `--chat-template-kwargs STRING` | sets additional params for the json template parser, must be a valid json object string, e.g. '{"key1":"value1","key2":"value2"}'<br/>(env: LLAMA_ARG_CHAT_TEMPLATE_KWARGS) |
| `--jinja, --no-jinja` | whether to use jinja template engine for chat (default: enabled)<br/>(env: LLAMA_ARG_JINJA) |
| `--reasoning-format FORMAT` | controls whether thought tags are allowed and/or extracted from the response, and in which format they're returned; one of:<br/>- none: leaves thoughts unparsed in `message.content`<br/>- deepseek: puts thoughts in `message.reasoning_content`<br/>- deepseek-legacy: keeps `<think>` tags in `message.content` while also populating `message.reasoning_content`<br/>(default: auto)<br/>(env: LLAMA_ARG_THINK) |
| `-rea, --reasoning [on\|off\|auto]` | Use reasoning/thinking in the chat ('on', 'off', or 'auto', default: 'auto' (detect from template))<br/>(env: LLAMA_ARG_REASONING) |
| `--spec-draft-n-min N` | minimum number of draft tokens to use for speculative decoding (default: 0)<br/>(env: LLAMA_ARG_SPEC_DRAFT_N_MIN) |
| `--spec-draft-p-split, --draft-p-split P` | speculative decoding split probability (default: 0.10)<br/>(env: LLAMA_ARG_SPEC_DRAFT_P_SPLIT) |
| `--spec-draft-p-min, --draft-p-min P` | minimum speculative decoding probability (greedy) (default: 0.00)<br/>(env: LLAMA_ARG_SPEC_DRAFT_P_MIN) |
+| `--spec-draft-backend-sampling, --no-spec-draft-backend-sampling` | offload draft sampling to the backend (default: enabled)<br/>(env: LLAMA_ARG_SPEC_DRAFT_BACKEND_SAMPLING) |
| `--spec-draft-device, -devd, --device-draft <dev1,dev2,..>` | comma-separated list of devices to use for offloading the draft model (none = don't offload)<br/>use --list-devices to see a list of available devices |
| `--spec-draft-ngl, -ngld, --gpu-layers-draft, --n-gpu-layers-draft N` | max. number of draft model layers to store in VRAM, either an exact number, 'auto', or 'all' (default: auto)<br/>(env: LLAMA_ARG_N_GPU_LAYERS_DRAFT) |
| `--spec-draft-model, -md, --model-draft FNAME` | draft model for speculative decoding (default: unused)<br/>(env: LLAMA_ARG_SPEC_DRAFT_MODEL) |
| `-hffv, --hf-file-v FILE` | Hugging Face model file for the vocoder model (default: unused)<br/>(env: LLAMA_ARG_HF_FILE_V) |
| `-hft, --hf-token TOKEN` | Hugging Face access token (default: value from HF_TOKEN environment variable)<br/>(env: HF_TOKEN) |
| `--log-disable` | Log disable |
-| `--log-file FNAME` | Log to file<br/>(env: LLAMA_LOG_FILE) |
-| `--log-colors [on\|off\|auto]` | Set colored logging ('on', 'off', or 'auto', default: 'auto')<br/>'auto' enables colors when output is to a terminal<br/>(env: LLAMA_LOG_COLORS) |
+| `--log-file FNAME` | Log to file<br/>(env: LLAMA_ARG_LOG_FILE) |
+| `--log-colors [on\|off\|auto]` | Set colored logging ('on', 'off', or 'auto', default: 'auto')<br/>'auto' enables colors when output is to a terminal<br/>(env: LLAMA_ARG_LOG_COLORS) |
| `-v, --verbose, --log-verbose` | Set verbosity level to infinity (i.e. log all messages, useful for debugging) |
-| `--offline` | Offline mode: forces use of cache, prevents network access<br/>(env: LLAMA_OFFLINE) |
-| `-lv, --verbosity, --log-verbosity N` | Set the verbosity threshold. Messages with a higher verbosity will be ignored. Values:<br/> - 0: generic output<br/> - 1: error<br/> - 2: warning<br/> - 3: info<br/> - 4: debug<br/>(default: 3)<br/><br/>(env: LLAMA_LOG_VERBOSITY) |
+| `--offline` | Offline mode: forces use of cache, prevents network access<br/>(env: LLAMA_ARG_OFFLINE) |
+| `-lv, --verbosity, --log-verbosity N` | Set the verbosity threshold. Messages with a higher verbosity will be ignored. Values:<br/> - 0: generic output<br/> - 1: error<br/> - 2: warning<br/> - 3: info<br/> - 4: trace (more info)<br/> - 5: debug<br/>(default: 3)<br/><br/>(env: LLAMA_ARG_LOG_VERBOSITY) |
| `--log-prefix, --no-log-prefix` | Enable prefix in log messages<br/>(env: LLAMA_ARG_LOG_PREFIX) |
| `--log-timestamps, --no-log-timestamps` | Enable timestamps in log messages<br/>(env: LLAMA_ARG_LOG_TIMESTAMPS) |
| `--spec-draft-type-k, -ctkd, --cache-type-k-draft TYPE` | KV cache data type for K for the draft model<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_SPEC_DRAFT_CACHE_TYPE_K) |
| `-hffv, --hf-file-v FILE` | Hugging Face model file for the vocoder model (default: unused)<br/>(env: LLAMA_ARG_HF_FILE_V) |
| `-hft, --hf-token TOKEN` | Hugging Face access token (default: value from HF_TOKEN environment variable)<br/>(env: HF_TOKEN) |
| `--log-disable` | Log disable |
-| `--log-file FNAME` | Log to file<br/>(env: LLAMA_LOG_FILE) |
-| `--log-colors [on\|off\|auto]` | Set colored logging ('on', 'off', or 'auto', default: 'auto')<br/>'auto' enables colors when output is to a terminal<br/>(env: LLAMA_LOG_COLORS) |
+| `--log-file FNAME` | Log to file<br/>(env: LLAMA_ARG_LOG_FILE) |
+| `--log-colors [on\|off\|auto]` | Set colored logging ('on', 'off', or 'auto', default: 'auto')<br/>'auto' enables colors when output is to a terminal<br/>(env: LLAMA_ARG_LOG_COLORS) |
| `-v, --verbose, --log-verbose` | Set verbosity level to infinity (i.e. log all messages, useful for debugging) |
-| `--offline` | Offline mode: forces use of cache, prevents network access<br/>(env: LLAMA_OFFLINE) |
-| `-lv, --verbosity, --log-verbosity N` | Set the verbosity threshold. Messages with a higher verbosity will be ignored. Values:<br/> - 0: generic output<br/> - 1: error<br/> - 2: warning<br/> - 3: info<br/> - 4: debug<br/>(default: 3)<br/><br/>(env: LLAMA_LOG_VERBOSITY) |
+| `--offline` | Offline mode: forces use of cache, prevents network access<br/>(env: LLAMA_ARG_OFFLINE) |
+| `-lv, --verbosity, --log-verbosity N` | Set the verbosity threshold. Messages with a higher verbosity will be ignored. Values:<br/> - 0: generic output<br/> - 1: error<br/> - 2: warning<br/> - 3: info<br/> - 4: trace (more info)<br/> - 5: debug<br/>(default: 3)<br/><br/>(env: LLAMA_ARG_LOG_VERBOSITY) |
| `--log-prefix, --no-log-prefix` | Enable prefix in log messages<br/>(env: LLAMA_ARG_LOG_PREFIX) |
| `--log-timestamps, --no-log-timestamps` | Enable timestamps in log messages<br/>(env: LLAMA_ARG_LOG_TIMESTAMPS) |
| `--spec-draft-type-k, -ctkd, --cache-type-k-draft TYPE` | KV cache data type for K for the draft model<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_SPEC_DRAFT_CACHE_TYPE_K) |
| `--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<br/>(env: LLAMA_ARG_SSL_KEY_FILE) |
| `--ssl-cert-file FNAME` | path to file a PEM-encoded SSL certificate<br/>(env: LLAMA_ARG_SSL_CERT_FILE) |
-| `--chat-template-kwargs STRING` | sets additional params for the json template parser, must be a valid json object string, e.g. '{"key1":"value1","key2":"value2"}'<br/>(env: LLAMA_CHAT_TEMPLATE_KWARGS) |
+| `--chat-template-kwargs STRING` | sets additional params for the json template parser, must be a valid json object string, e.g. '{"key1":"value1","key2":"value2"}'<br/>(env: LLAMA_ARG_CHAT_TEMPLATE_KWARGS) |
| `-to, --timeout N` | server read/write timeout in seconds (default: 600)<br/>(env: LLAMA_ARG_TIMEOUT) |
| `--threads-http N` | number of threads used to process HTTP requests (default: -1)<br/>(env: LLAMA_ARG_THREADS_HTTP) |
| `--cache-prompt, --no-cache-prompt` | whether to enable prompt caching (default: enabled)<br/>(env: LLAMA_ARG_CACHE_PROMPT) |
| `--spec-draft-n-min N` | minimum number of draft tokens to use for speculative decoding (default: 0)<br/>(env: LLAMA_ARG_SPEC_DRAFT_N_MIN) |
| `--spec-draft-p-split, --draft-p-split P` | speculative decoding split probability (default: 0.10)<br/>(env: LLAMA_ARG_SPEC_DRAFT_P_SPLIT) |
| `--spec-draft-p-min, --draft-p-min P` | minimum speculative decoding probability (greedy) (default: 0.00)<br/>(env: LLAMA_ARG_SPEC_DRAFT_P_MIN) |
+| `--spec-draft-backend-sampling, --no-spec-draft-backend-sampling` | offload draft sampling to the backend (default: enabled)<br/>(env: LLAMA_ARG_SPEC_DRAFT_BACKEND_SAMPLING) |
| `--spec-draft-device, -devd, --device-draft <dev1,dev2,..>` | comma-separated list of devices to use for offloading the draft model (none = don't offload)<br/>use --list-devices to see a list of available devices |
| `--spec-draft-ngl, -ngld, --gpu-layers-draft, --n-gpu-layers-draft N` | max. number of draft model layers to store in VRAM, either an exact number, 'auto', or 'all' (default: auto)<br/>(env: LLAMA_ARG_N_GPU_LAYERS_DRAFT) |
| `--spec-draft-model, -md, --model-draft FNAME` | draft model for speculative decoding (default: unused)<br/>(env: LLAMA_ARG_SPEC_DRAFT_MODEL) |
overview / pkg / ggml / sources / llama.cpp / commitdiff