Commit History

Author SHA1 Message Date
  50h100a 43c9858854 Merge pull request #244 from PygmalionAI/faster_topk 9 months ago
  50h100a bd564148e2 Merge branch 'main' of https://github.com/PygmalionAI/aphrodite-engine into ffs 9 months ago
  50h100a d3dd170a7d merge main 9 months ago
  AlpinDale 78d66f16d1 Chunked Prefill Part 1 (#384) 9 months ago
  AlpinDale 9181fa0396 feat: Triton kernels for sampling (#383) 9 months ago
  50h100a dc09dc2b4d Merge branch 'main' into pr_samplers 10 months ago
  AlpinDale f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 10 months ago
  50h100a 7ed57e318d Overhauled SamplingTensors construction. 10 months ago
  50h100a d5dbd29db4 hoist sampler internals into a single function. 10 months ago
  AlpinDale da223153c6 feat&fix: cohere support and missing GPU blocks (#333) 10 months ago
  AlpinDale e42a78381a feat: switch from pylint to ruff (#322) 10 months ago
  AlpinDale 9fa99215f8 feat: add cubic sampling (#280) 11 months ago
  AlpinDale 657aec0cbd refactor: OpenAI endpoint (#261) 11 months ago
  AlpinDale 4d04ade9ef feat: fine-grained seeds (#279) 11 months ago
  anon998 35b9033782 fix: crash in quadratic sampling when batch > 1 (#253) 11 months ago
  50h100a f619c96c79 fix: zero token output due to temperature bias (#243) 1 year ago
  50h100a 53a9c60442 fix: logit processor declarations and application (#242) 1 year ago
  50h100a 2e3318c1fa yapf considers this space to be CRITICAL 1 year ago
  50h100a 25acebe33d better variable naming 1 year ago
  50h100a 7b3bb995c1 topk as linear write 1 year ago
  AlpinDale e73a92ad2f fix: remove the mask for quadratic sampling (#236) 1 year ago
  AlpinDale 1c46fa31ad feat: add quadratic sampling (#233) 1 year ago
  AlpinDale c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) 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
  Stefan Gligorijevic 9e7e108dc8 chore: clamp dynatemp_min (#214) 1 year ago
  Stefan Gligorijevic 56446a04bb feat: dynamic temperature (#209) 1 year ago
  AlpinDale d54791aaa8 feat: reduce sampler overhead by making it less blocking (#198) 1 year ago
  AlpinDale 653da510d1 chore: rewrite InputMetadata (#143) 1 year ago
  AlpinDale 6c914ea0e4 fix: `SequenceOutputs` -> `SequenceOutput` (#133) 1 year ago