Easy, fast, and cheap LLM serving for everyone vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: Efficient management

  • 37articles · 30d
  • 4+ day agolatest article
  • Aug 15, 2026earliest in window
  • 0%with images
  • 177avg words
articles per day
Categories
  • Science & Technology 37
  • Software Dev. 37
  • Computers & Electronics 36
  • Jobs & Education 1

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 > entrypoints > serve > engine > protocol

protocol

2+ week, 1+ hour ago   (53+ words) vLLM Prompt tokens contributed by each input modality, keyed by modality name multimodal_tokens = None class-attribute instance-attribute ¶ Prompt tokens contributed by each input modality, keyed by modality name (e.g. image, audio, video ). A breakdown of the multimodal placeholder tokens already counted…...

vLLM
docs.vllm.ai > en > latest > api > vllm > models > qwen4_exp > amd > low_latency_gemm

low_latency_gemm

2+ week, 2+ hour ago   (20+ words) vLLM Qwen4Exp low-latency GEMM hook for AMD ROCm. Keep the standard vLLM linear methods on AMD ROCm....

vLLM
docs.vllm.ai > en > latest > api > vllm > models > qwen4_exp > nvidia > model

model

2+ week, 2+ hour ago   (106+ words) Return all MambaSpecs for this model (GDN layers + PLE layer). The PLE layer uses a separate short_conv MambaSpec whose page_size_bytes may exceed the GDN spec; callers should take the maximum. Qwen3-VL vision tower backed by the Qwen4Exp language model. Expose Qwen4Exp routed experts through…...

vLLM
docs.vllm.ai > en > latest > api > vllm > models > qwen4_exp > nvidia > model_state

model_state

2+ week, 2+ hour ago   (18+ words) vLLM Model-runner state for Qwen4Exp PLE inputs. Add rollback-safe PLE n-gram context to the model inputs....

vLLM
docs.vllm.ai > en > latest > api > vllm > tool_parsers > hy_v4_tool_parser

hy_v4_tool_parser

2+ week, 22+ hour ago   (620+ words) Pure tool-call parsing logic for HYV4. Returns plain dicts; no vLLM types. Holds only parser state: the structural token strings/ids, the compiled regexes, and the streaming incremental state. Stateless argument parsing is delegated to the module-level utilities above. Streaming has…...

vLLM
docs.vllm.ai > en > latest > api > vllm > entrypoints > openai > sse_keep_alive

sse_keep_alive

3+ week, 8+ hour ago   (48+ words) vLLM SSE keep-alive comments for idle streaming responses. Emit an SSE keep-alive comment when generator is idle. A non-positive or non-finite interval returns generator unchanged, so the default path has no overhead. Otherwise a keep-alive comment is yielded whenever no…...

vLLM
docs.vllm.ai > en > latest > api > vllm > models > deepseek_v32 > nvidia > glm52_low_latency_gemm

glm52_low_latency_gemm

1+ mon, 1+ week ago   (26+ words) vLLM GLM-5.2 decode GEMM selection for unquantized BF16 on SM103. Plan for a weight the walk below cannot reach (a plain nn.Linear )....

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

server_utils

3+ week, 4+ day 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 > tool_parsers > dots_tool_parser

dots_tool_parser

4+ 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…...