Hackernews posts about VLLM

RSS feed for VLLM

61
newSpeculative Decoding in vLLM on AMD GPUsvllm.ai
▲ 145ankitg12 28d 💬 53
62
newSelf-hosted inference orchestrators compared: LocalAI, exo, GPUStack, vLLMwww.nexlab.net
▲ 13nextime 14d 💬 7
63
newWatermarking in vLLMvllm.ai
▲ 3eatonphil 10d discuss
64
newKeeping vLLM's Prefix Cache Warm Between Agent Turnsdoug.sh
▲ 3dougcalobrisi 16d discuss
65
newvLLM 0.29.0: Model Runner V2 is now the defaultgithub.com
▲ 3joshcsimmons 26d discuss
66
newGlq a port trellis quantization of large language models as a vLLM plugingithub.com
▲ 2acd 25d 💬 1
67
newCustom Models in Oh My Pi: vLLM, Llama.cpp, SGLang and Moredoug.sh
▲ 2dougcalobrisi 9d discuss
68
newvLLM Architecture, Memory and Benchmarks Deep Divewww.g-ftech.com
▲ 2gfactor_ai 13d discuss
69
newServing LLMs on Tenstorrent Hardware: Inside the vLLM TT Pluginvllm.ai
▲ 2ankitg12 24d discuss
70
newHow to build a Jev-style classifier with DiffusionGemma and vLLMmedium.com
▲ 1teleforce 7d 💬 2
71
newShow HN: InferPilot – the vLLM doctor that tells you when fp8 won't helpgithub.com
▲ 1poojithdevan 4d discuss
72
newShow HN: Reflex Engine Beats Both Llama.cpp and vLLM on Cold-Start to TTFTgithub.com
▲ 1leochong 5d discuss
73
newContextMemory – Markdown memory for your llama.cpp/vLLM servergithub.com
▲ 1vitorcastro78 6d discuss
74
newRun Decision Models on vLLM and Red Hat AI Using DiffusionGemmadevelopers.redhat.com
▲ 1thebeardisred 6d discuss
75
newWhat one vLLM replica on an L40 can carry and how it failspercentes.ai
▲ 1itsveems 9d discuss
76
newHardware-Agnostic Models in vLLMpytorch.org
▲ 1matt_d 12d discuss
77
newvLLM: Jev-like mode for the DiffusionGemma modelgithub.com
▲ 1mmastrac 18d discuss
78
newShow HN: Self-adjusting vLLM at production scaletwitter.com
▲ 1dmitriisn 19d discuss
79
newLaunch HN: Magnitude (YC S25) – Self-optimizing inference engine for agentsgithub.com
▲ 194anerli 4d 💬 99
80
newTurning GLM-5.3-Flash into a Jev-like decision modelwww.privatemode.ai
▲ 138flxflx 9d 💬 59
81
newShow HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and costnarilabs.com
▲ 92toebee 21d 💬 31
82
newShow HN: Recursant, the agent-aware model router built for hybrid workloadsgithub.com
▲ 1hestefisk 12h discuss
83
newShow HN: MaskShift – a maximalist coding agent with zero NPM dependenciesgithub.com
▲ 1Nafeeur 28d discuss
84
newDecision 2.0: our newest decision modelstwitter.com
▲ 3thedima 18h discuss