Commit Verlauf

Autor SHA1 Nachricht Datum
  AlpinDale be8154a8a0 feat: proper embeddings API with e5-mistral-7b support vor 6 Monaten
  AlpinDale d287afd917 optimize get_logprobs vor 6 Monaten
  AlpinDale 79901b76de logprobs for target model (spec decoding) vor 6 Monaten
  AlpinDale 35ae01d7ba refactor: attention metadata term vor 6 Monaten
  AlpinDale ccf4d5cab6 disable banned tokens vor 6 Monaten
  AlpinDale 9ce319b03c fix: sampler indexing issues in distributed environments (#546) vor 6 Monaten
  AlpinDale 772b4a4504 temporarily disable dynatemp vor 6 Monaten
  AlpinDale b178bc12b3 fix min_tokens when eos_token_id is None vor 6 Monaten
  AlpinDale 7d3194e7f4 revert #244 vor 6 Monaten
  AlpinDale aed64884c6 feat: prompt logprobs with chunked prefill (#539) vor 6 Monaten
  AlpinDale fca911ee0a vLLM Upstream Sync (#526) vor 7 Monaten
  AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388) vor 9 Monaten
  50h100a f663d3fccc Merge pull request #397 from 50h100a/pr_samplerasserts vor 10 Monaten
  50h100a 85ae23ac3c Missed .items() and assert vor 10 Monaten
  50h100a 43c9858854 Merge pull request #244 from PygmalionAI/faster_topk vor 10 Monaten
  50h100a bd564148e2 Merge branch 'main' of https://github.com/PygmalionAI/aphrodite-engine into ffs vor 10 Monaten
  50h100a d3dd170a7d merge main vor 10 Monaten
  AlpinDale 78d66f16d1 Chunked Prefill Part 1 (#384) vor 10 Monaten
  AlpinDale 9181fa0396 feat: Triton kernels for sampling (#383) vor 10 Monaten
  50h100a dc09dc2b4d Merge branch 'main' into pr_samplers vor 10 Monaten
  AlpinDale f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) vor 10 Monaten
  50h100a 7ed57e318d Overhauled SamplingTensors construction. vor 10 Monaten
  50h100a d5dbd29db4 hoist sampler internals into a single function. vor 10 Monaten
  AlpinDale da223153c6 feat&fix: cohere support and missing GPU blocks (#333) vor 11 Monaten
  AlpinDale e42a78381a feat: switch from pylint to ruff (#322) vor 11 Monaten
  AlpinDale 9fa99215f8 feat: add cubic sampling (#280) vor 11 Monaten
  AlpinDale 657aec0cbd refactor: OpenAI endpoint (#261) vor 11 Monaten
  AlpinDale 4d04ade9ef feat: fine-grained seeds (#279) vor 11 Monaten
  anon998 35b9033782 fix: crash in quadratic sampling when batch > 1 (#253) vor 1 Jahr
  50h100a f619c96c79 fix: zero token output due to temperature bias (#243) vor 1 Jahr