LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

  • Markets
  • Builders
  • Research
  • Ecosystems
  • Launchpads
  • Search
Ecosystems

Python

SpecForgeLocalDev

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

PythonEmerging
GitHubWebsite
Stars
—
Forks
—
Contributors
8
Last push
7mo ago

Recent commits

Latest commits.

  • updated test workflow container settings (#286)
    85b1e94Shenggui Li7mo ago
  • add template for deepseek-r1-distill (#281)
    39bd14cBao Jiangnan7mo ago
  • fix bugs prepare_generate_hidden_states use dp (#283)
    d5de56fjiapingW7mo ago
  • added vocab_paralell_embedding and parallel_lm_head (#284)
    660b2b7Shenggui Li7mo ago
  • support prepare hidden states use dp (#282)
    35504d4jiapingW7mo ago
Added requirements-rocm.txt for AMD GPU and ROCm (#275)
cd97516ChangLiu07097mo ago
  • added abstraction for target model backend (#278)
    ba6159cShenggui Li7mo ago
  • fixed the workflow on CI runner (#276)
    c5549baShenggui Li7mo ago

    • Top contributors

    Builders behind this project.

    FrankLeeeee
    22 commits
    fzyzcjy
    12 commits
    sleepcoo
    7 commits
    shimizust
    7 commits
    Ximingwang-09
    6 commits
    yubofredwang
    6 commits
    ZhengHSI
    6 commits
    jiapingW
    5 commits