diff --git a/tools/cli/README.md b/tools/cli/README.md
index b11aa45ce9..988957f711 100644
--- a/tools/cli/README.md
+++ b/tools/cli/README.md
@@ -161,9 +161,12 @@
| `-mmu, --mmproj-url URL` | URL to a multimodal projector file. see tools/mtmd/README.md
(env: LLAMA_ARG_MMPROJ_URL) |
| `--mmproj-auto, --no-mmproj, --no-mmproj-auto` | whether to use multimodal projector file (if available), useful when using -hf (default: enabled)
(env: LLAMA_ARG_MMPROJ_AUTO) |
| `--mmproj-offload, --no-mmproj-offload` | whether to enable GPU offloading for multimodal projector (default: enabled)
(env: LLAMA_ARG_MMPROJ_OFFLOAD) |
-| `--image, --audio FILE` | path to an image or audio file. use with multimodal models, use comma-separated values for multiple files |
+| `--image, --audio, --video FILE` | path to an image, audio, or video 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)
(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)
(env: LLAMA_ARG_IMAGE_MAX_TOKENS) |
+| `--video-fps N` | target video frame rate (default: 4.0)
(env: LLAMA_ARG_VIDEO_FPS) |
+| `--video-timestamp-interval N` | interval in milliseconds between text timestamps (default: 5000)
(env: LLAMA_ARG_VIDEO_TIMESTAMP_INTERVAL) |
+| `--video-ffmpeg-dir DIR` | path to the directory containing ffmpeg and ffprobe (default: search in PATH)
(env: LLAMA_ARG_VIDEO_FFMPEG_DIR) |
| `--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"}'
(env: LLAMA_ARG_CHAT_TEMPLATE_KWARGS) |
| `--jinja, --no-jinja` | whether to use jinja template engine for chat (default: enabled)
(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:
- none: leaves thoughts unparsed in `message.content`
- deepseek: puts thoughts in `message.reasoning_content`
- deepseek-legacy: keeps `` tags in `message.content` while also populating `message.reasoning_content`
(default: auto)
(env: LLAMA_ARG_THINK) |
diff --git a/tools/server/README.md b/tools/server/README.md
index f507b8c181..4c45d4f78b 100644
--- a/tools/server/README.md
+++ b/tools/server/README.md
@@ -175,13 +175,14 @@ For the full list of features, please refer to [server's changelog](https://gith
| `-np, --parallel N` | number of server slots (default: -1, -1 = auto)
(env: LLAMA_ARG_N_PARALLEL) |
| `-cb, --cont-batching, -nocb, --no-cont-batching` | whether to enable continuous batching (a.k.a dynamic batching) (default: enabled)
(env: LLAMA_ARG_CONT_BATCHING) |
| `-mm, --mmproj FILE` | path to a multimodal projector file. see tools/mtmd/README.md
note: if -hf is used, this argument can be omitted
(env: LLAMA_ARG_MMPROJ) |
-| `-tk, --talker-model FILE` | path to the qwen3-omni talker gguf, enables the /v1/audio/speech endpoint
(env: LLAMA_ARG_TALKER_MODEL) |
-| `-c2w, --code2wav-model FILE` | path to the qwen3-omni code2wav gguf, the talker code detokenizer
(env: LLAMA_ARG_CODE2WAV_MODEL) |
| `-mmu, --mmproj-url URL` | URL to a multimodal projector file. see tools/mtmd/README.md
(env: LLAMA_ARG_MMPROJ_URL) |
| `--mmproj-auto, --no-mmproj, --no-mmproj-auto` | whether to use multimodal projector file (if available), useful when using -hf (default: enabled)
(env: LLAMA_ARG_MMPROJ_AUTO) |
| `--mmproj-offload, --no-mmproj-offload` | whether to enable GPU offloading for multimodal projector (default: enabled)
(env: LLAMA_ARG_MMPROJ_OFFLOAD) |
| `--image-min-tokens N` | minimum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)
(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)
(env: LLAMA_ARG_IMAGE_MAX_TOKENS) |
+| `--video-fps N` | target video frame rate (default: 4.0)
(env: LLAMA_ARG_VIDEO_FPS) |
+| `--video-timestamp-interval N` | interval in milliseconds between text timestamps (default: 5000)
(env: LLAMA_ARG_VIDEO_TIMESTAMP_INTERVAL) |
+| `--video-ffmpeg-dir DIR` | path to the directory containing ffmpeg and ffprobe (default: search in PATH)
(env: LLAMA_ARG_VIDEO_FFMPEG_DIR) |
| `-a, --alias STRING` | set model name aliases, comma-separated (to be used by API)
(env: LLAMA_ARG_ALIAS) |
| `--tags STRING` | set model tags, comma-separated (informational, not used for routing)
(env: LLAMA_ARG_TAGS) |
| `--embd-normalize N` | normalisation for embeddings (default: 2) (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm) |
@@ -207,6 +208,7 @@ For the full list of features, please refer to [server's changelog](https://gith
| `--ssl-cert-file FNAME` | path to file a PEM-encoded SSL certificate
(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"}'
(env: LLAMA_ARG_CHAT_TEMPLATE_KWARGS) |
| `-to, --timeout N` | server read/write timeout in seconds (default: 3600)
(env: LLAMA_ARG_TIMEOUT) |
+| `--sse-ping-interval N` | server SSE ping interval in seconds (-1 = disabled, default: 30)
(env: LLAMA_ARG_SSE_PING_INTERVAL) |
| `--threads-http N` | number of threads used to process HTTP requests (default: -1)
(env: LLAMA_ARG_THREADS_HTTP) |
| `--cache-prompt, --no-cache-prompt` | whether to enable prompt caching (default: enabled)
(env: LLAMA_ARG_CACHE_PROMPT) |
| `--cache-reuse N` | min chunk size to attempt reusing from the cache via KV shifting, requires prompt caching to be enabled (default: 0)
[(card)](https://ggml.ai/f0.png)
(env: LLAMA_ARG_CACHE_REUSE) |