Please confirm you are human

This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.

A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.

Hold with a pointer, or hold Space or Enter.

News

vLLM
docs.vllm.ai > en > latest > api > vllm > models > kimi_k3 > nvidia > kda_metadata

kda_metadata

3+ week, 4+ day ago   (57+ words) vLLM Kimi-K3 specialization of GDN attention metadata. The request classification and cudagraph staging intentionally mirror GDNAttentionMetadataBuilder. Kimi-K3 builds the metadata required by its prefill KDA kernel internally, so this builder omits the shared FLA chunk metadata construction. For Kimi-K3 speculative…...

vLLM
docs.vllm.ai > en > latest > api > vllm > model_executor > layers > fused_moe > router > fused_topk_bias_router

fused_topk_bias_router

7+ mon, 5+ day ago   (21+ words) vLLM Router using fused top-k with e_score_correction_bias. Compute routing using fused top-k with bias....

vLLM
docs.vllm.ai > en > latest > api > vllm > model_executor > models > moonvit

moonvit

9+ mon, 2+ week ago   (284+ words) Build packed per-token positional embeddings for a list of grids. whether to use bias in linear layer. precomputed positional embeddings of shape (L, Cout). When provided, grid_hw is unused and the CUDA-graph-incompatible interpolation in self.pos_emb is skipped. Optional precomputed scalar tensor....

vLLM
docs.vllm.ai > en > latest > usage > metrics

Production Metrics

9+ mon, 2+ week ago   (92+ words) vLLM exposes a number of metrics that can be used to monitor the health of the system. These metrics are exposed via the /metrics endpoint on the vLLM OpenAI compatible API server. You can start the server using Python, or…...

vLLM
docs.vllm.ai > en > latest > api > vllm > entrypoints > launchers > utils > server_utils

server_utils

4+ day, 7+ hour ago   (47+ words) vLLM Get the uvicorn log config based on the provided arguments. Priority: 1. If log_config_file is specified, use it 2. If disable_access_log_for_endpoints is specified, create a config with the access log filter 3. Otherwise, return None (use uvicorn defaults)...

vLLM
docs.vllm.ai > en > latest > api > vllm > entrypoints > anthropic > protocol

protocol

9+ mon, 2+ week ago   (48+ words) Pydantic models for Anthropic API protocol Content block in message Delta for streaming responses Error structure for Anthropic API Error response structure for Anthropic API JSON output format configuration Anthropic Messages API request Anthropic Messages API response Configuration options for…...

vLLM
docs.vllm.ai > en > latest > api > vllm > model_executor > models > glm_ocr

glm_ocr

6+ mon, 3+ week ago   (10+ words) vLLM Inference-only GLM-OCR model compatible with HuggingFace weights....

Google News
docs.vllm.ai > en > latest > api > vllm > models > dots3_note > nvidia > audio

audio

1+ week, 1+ day ago   (22+ words) vLLM _forward_speech_encoder(mel_features, input_seq_lens, audio_sample_lens) ¶ Run the eager speech encoder without server-side slicing/batching....

vLLM
docs.vllm.ai > en > latest > api > vllm > tool_parsers > dots_tool_parser

dots_tool_parser

1+ week, 1+ day ago   (55+ words) vLLM Parse Dots tool calls in their XML wrapper format. The canonical body contains one or more invoke elements:: A JSON object with name and arguments is also accepted as a fallback. Multiple wrapper blocks and multiple invokes per block…...

vLLM
docs.vllm.ai > en > latest > api > vllm > model_executor > hw_agnostic > layers > layernorm

layernorm

1+ week, 3+ day ago   (33+ words) vLLM _fused_add_rms_norm(x, x_residual, weight, epsilon, variance_size=None) ¶ Fused add and weighted root-mean-square layer normalization _rms_norm(x, weight, epsilon, variance_size=None) ¶ Weighted root-mean-square layer normalization...