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
  • 3+ 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 > models > deepseek_v4 > cpu > dspark

dspark

3+ day, 48+ min ago   (47+ words) vLLM CPU DeepSeek-V4 DSpark (speculative decoding) — deferred, not implemented. DSparkDeepseekV4ForCausalLM is only instantiated when the speculative- decoding registry resolves it by name for a DSpark speculative config; a plain (non-spec) DeepSeek-V4 CPU model never constructs this class. This stub exists solely…...

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

low_latency_gemm

1+ week, 5+ day 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 > amd > indexer_qsa

indexer_qsa

1+ week, 5+ day ago   (49+ words) Replicated Q/K projection plus paged, weight-free QSA selection. Normalize pooled K and apply the first token's exact group position. Project replicated Q/K, normalize+rotate Q, and preserve raw K. Use vLLM's portable RMSNorm implementation on ROCm. Apply the main…...

vLLM
docs.vllm.ai > en > latest > api > vllm > reasoning > hy_v4_reasoning_parser

hy_v4_reasoning_parser

1+ week, 6+ day ago   (286+ words) Reasoning extraction for HYV4, on plain data. Count reasoning tokens (0 in no_think). The start token is injected at the END of the prompt, so it is normally absent from token_ids. Only skip a leading start token when it actually appears first (legacy / no…...

vLLM
docs.vllm.ai > en > latest > api > vllm > models > hy_v4 > nvidia > flashmla_sparse

flashmla_sparse

1+ week, 6+ day ago   (254+ words) Sink-capable FlashMLA sparse backend for HY V4 (NVIDIA). HY V4 adds a per-head learnable attention sink on top of sparse MLA. The vendored FlashMLA kernels already accept an attn_sink argument, but vLLM's shared FLASHMLA_SPARSE backend neither advertises sink support nor forwards the tensor, so…...

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

hy_v4_tool_parser

1+ week, 6+ day 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

2+ week, 6+ day 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 > distributed > weight_transfer > sharded_rdt_engine

sharded_rdt_engine

2+ week, 6+ day ago   (1746+ words) Sharded Ray Direct Transport (RDT) weight transfer engine (consumer side). Pulls only the slice each vLLM worker consumes under tensor/expert parallelism, not the full HF-format tensor. One thing at four resolutions, over three lifetimes. FetchKey -- (name, op_chain), "which slice of…...

vLLM
docs.vllm.ai > en > latest > training > weight_transfer > sharded_rdt

Sharded RDT Engine

2+ week, 6+ day ago   (259+ words) Discovery is expensive, so it happens once, at init_transfer_engine, as a dry run over model.load_weights with every parameter on meta. Nothing is transferred; the engine just records, per leaf module, which slice feeds which destination region. Every later sync is pure…...

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

server_utils

3+ week, 3+ 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)...