rustformers/llm Issues
Multi-GPU support for inferencing
Updated 1Fix tensor name API
ClosedSupport GGUF
Updated 4Chat does not halt
ClosedBloom 176B inference is broken
Updated 10Using gpu is slower as not using it
Updated 4Info on getting models?
Closed 1cuBLAS error
Updated 11Building with clblast
Closed 7build failure on orin agx
Updated 3Paged Attention
Updated 10Better generation stats
Updated 4Support new quantization formats
Closed 2WeightedIndex error: invalid weight
Updated 6Modular sampler
Closed 3CUDA decoding
Closed 16Implement jsonformer
Closed 2Support WebGPU acceleration?
Updated 1Nix Flake
Closed 1Support ggml metal backend
Closed 29Better embedding extraction
Updated 1invalid file format version 2
Closed 9Support Falcon
Updated 10failed to load LLaMA model
Closed 4