llama.cpp

llama.cpp appears in 19 Vector Wire stories since August, 3 of them about llama.cpp itself.

Stories About llama.cpp

3

Ollama v0.33.3-rc0 Bumps llama.cpp to b10729Alert · Sep 2

• Sep 25Ollama v0.40.0-rc0 Adds Manifest-List Storage, Drops llama.cpp Compatibility PatchAlert · Sep 25
• Sep 16Ollama Ships v0.34.2 Release Candidate With llama.cpp UpdatesAlert · Sep 16

Also Mentioned In

16

• Oct 14LiquidAI ships LFM2.5-24B-A2B, a 24B reasoning model that activates only 2B parametersOct 14
• Oct 8Unsloth v0.1.904 Converts Any LLM Into a Decision ModelOct 8
• Oct 7Google DeepMind opens 740M-parameter multimodal embedding model under Apache 2.0Oct 7
• Oct 6Unsloth Adds Built-in Browser Panel, EmbeddingGemma 2, Audio Tools in v0.1.903 BetaOct 6
• Oct 6KV cache becomes programmable infrastructure across the inference stackOct 6

More stories that mention llama.cpp

• Sep 30Axolotl v0.20.0 Adds GGUF Export, Context Parallelism, NVFP4 LoRASep 30
• Sep 28Unsloth Adds Local Decision Models, 4.5× Faster Image GenerationSep 28
• Sep 16vLLM consolidates as default LLM serving layer across chips, clouds, and consumer GPUsSep 16
• Sep 15Ollama v0.34.1 Patches MLX Memory, Raises Token Repeat LimitSep 15
• Sep 10Quantization moves from checkpoint to serving engine as practitioners tune per workloadSep 10
• Sep 9Unsloth v0.1.808 Delivers 1.7x Faster Diffusion, 250-Plus Bug FixesSep 9
• Sep 1Consumer GPUs now serve 27B models past 100 tok/s as software eats the inference moatSep 1
• Aug 27Unsloth Adds Local Inference for Qwen3.8-Flash-Next and GLM-5.3-FlashAug 27
• Aug 22Alibaba Open-Sources Qwen3.8-27B: Frontier-Class AI on 17GB of RAMAug 22
• Aug 21Liquid AI Ships Speculative Decoding for LFM2.5, Claims Up to 3.18x GPU SpeedupAug 21
• Aug 15Running 2.45T-Parameter Models on Desktop GPUs: Local Inference Pushes LimitsAug 15