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 > v1 > fault_tolerance > engine_core_sentinel

engine_core_sentinel

4+ hour, 18+ min ago   (60+ words) Manages fault tolerance state for a single engine core. Push current health to the client so it can refresh its cache. Reinit DP process group if in DP mode. Returns worker params. Dispatch an FT command by instruction name. Called…...

vLLM
docs.vllm.ai > en > latest > api > vllm > models > inkling > nvidia > ops > fa4_rel_attention

fa4_rel_attention

1+ week, 2+ day ago   (82+ words) vLLM Round the FA4 scheduling bound up to a power of two. Return the split-KV cap for FA4 with sheared relative bias. Paged varlen FA4 over the bound K/V cache with the Inkling relative bias. q is (num_tokens, num_heads, head_dim); key_cache / value_cache are the paged caches (num_blocks, block_size, num_kv_heads, head_dim); block_table is…...

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

vllm.model_executor.models.openai_privacy_filter

3+ week, 5+ day ago   (46+ words) vLLM docs Inference-only OpenAI Privacy Filter model. gpt-oss reused as a bidirectional encoder for token classification: every layer runs non-causal attention with a banded ±sliding_window mask, and the LM head is replaced with a 33-class BIOES score head....

vLLM docs
docs.vllm.ai > en > stable > api > vllm > model_executor > layers > mamba > ops > gdn_chunk_cutedsl > kernel_kkt_inv_uw

vllm.model_executor.layers.mamba.ops.gdn_chunk_cutedsl.kernel_kkt_inv_uw

1+ mon, 2+ week ago   (19+ words) vLLM docs Compute per-chunk KKT inverse preprocessing and U/W tiles....

vLLM Docs
docs.vllm.ai > en > v0.18.1 > api > vllm > tool_parsers > phi4mini_tool_parser

phi4mini_tool_parser

3+ mon, 2+ week ago   (41+ words) vLLM Docs Tool call parser for phi-4-mini models intended for use with the examples/tool_chat_template_llama.jinja template. Used when --enable-auto-tool-choice --tool-call-parser phi4_mini_json are all set Extract the tool calls from a complete model response....