Commit History

Author SHA1 Message Date
  AlpinDale 1c46fa31ad feat: add quadratic sampling (#233) 11 months ago
  AlpinDale f0dacc17dd fix: remove fast-hadamard-transform in requirements 11 months ago
  AlpinDale 5d288aa76c feat: add fast hadamard transformation kernels (#232) 11 months ago
  AlpinDale 12fb635f70 readme: add docker 11 months ago
  AlpinDale eb8698c7bd readme: update with new benchmarks 1 year ago
  AlpinDale 59df05f341 feat: add `/metrics` route for kobold (#229) 1 year ago
  AlpinDale c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) 1 year ago
  AlpinDale 6305e6f3f2 fix: no repeated IPC registration (#227) 1 year ago
  AlpinDale 0adab894fe feat: grammar support (#206) 1 year ago
  AlpinDale 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 year ago
  AlpinDale c0146ed00e chore: slight refactor for async engine finish (#225) 1 year ago
  AlpinDale 339c6aec53 chore: bump ray version 1 year ago
  AlpinDale 641bb0f6e9 feat: add custom allreduce kernels (#224) 1 year ago
  AlpinDale 26a717b49f fix: use head_dim if available 1 year ago
  AlpinDale 5053743c1c feat: speedup AWQ (#223) 1 year ago
  AlpinDale c0aac15421 feat: S-LoRA support (#222) 1 year ago
  AlpinDale 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 year ago
  AlpinDale 3188d5690c fix: logprobs at -inf (#219) 1 year ago
  Stefan Gligorijevic 2b8421c3f7 more shape fixing 1 year ago
  Stefan Gligorijevic 6bdb466dda fix combining masks 1 year ago
  Stefan Gligorijevic 505fbc0c6b fix shapes 1 year ago
  Stefan Gligorijevic f4d5b4601c I am retarded 1 year ago
  Stefan Gligorijevic fac9e97bb3 fix scattering 1 year ago
  Stefan Gligorijevic 5d9182d018 oversight in logical or 1 year ago
  Stefan Gligorijevic b18fb39c48 I have no idea what i'm doing 1 year ago
  Stefan Gligorijevic ce0abe6df9 brainfart 1 year ago
  Stefan Gligorijevic 6807035070 typo 1 year ago
  Stefan Gligorijevic 6594a5de31 type brainfart 1 year ago
  Stefan Gligorijevic 3298547f99 Add sampler ordering 1 year ago
  AlpinDale a39eeb7188 fix: logprobs for dynatemp (#215) 1 year ago