llama.cpp
d9d54e49 - speculative : refactor and add a simpler example (#10362)
Commit
View On GitHub
Commit
197 days ago
speculative : refactor and add a simpler example (#10362) * speculative : refactor and add a simpler example ggml-ci * speculative : clean-up and add comments and TODOs [no ci] * speculative : manage context in common_speculative ggml-ci * speculative : simplify ggml-ci * speculative : simplify (cont) ggml-ci * speculative : add --draft-min CLI arg * speculative : minor fixup * make : build fixes * speculative : do not redraft previous drafts ggml-ci * speculative : fix the draft sampling ggml-ci * speculative : fix compile warning * common : refactor args ggml-ci * common : change defaults [no ci] * common : final touches ggml-ci
Author
ggerganov ggerganov
Parents
cce5a900
  • File
    Makefile
  • common
    • File
      CMakeLists.txt
    • File
      arg.cpp
    • File
      common.cpp
    • File
      common.h
    • File
      sampling.cpp
    • File
      sampling.h
    • File
      speculative.cpp
    • File
      speculative.h
  • examples
    • File
      CMakeLists.txt
    • batched
      • File
        batched.cpp
    • infill
      • File
        infill.cpp
    • llava
      • File
        llava-cli.cpp
      • File
        minicpmv-cli.cpp
    • lookahead
      • File
        lookahead.cpp
    • lookup
      • File
        lookup-stats.cpp
      • File
        lookup.cpp
    • main
      • File
        main.cpp
    • parallel
      • File
        parallel.cpp
    • retrieval
      • File
        retrieval.cpp
    • save-load-state
      • File
        save-load-state.cpp
    • server
      • File
        server.cpp
      • File
        utils.hpp
    • speculative-simple
      • File
        CMakeLists.txt
      • File
        README.md
      • File
        speculative-simple.cpp
    • speculative
      • File
        speculative.cpp
  • tests
    • File
      test-arg-parser.cpp
FAQ Terms Privacy Refunds Impressum