llama.cpp
f486f6e1 - ggml : add numa options (#5377)

Commit
1 year ago
ggml : add numa options (#5377) * Added numa options to allow finer grained control as well as plumbing for a new mirror mode that will require numa.h * Reverted Makefile * Fixed include * Removed sched.h from ggml.h, moved ggml_get_numa_affinity into ggml.c, removed trailing whitespace and fixed up a few inconsistent variables * removed trailing whitespace * Added numa options to allow finer grained control as well as plumbing for a new mirror mode that will require numa.h * Reverting Makefile * Fixed a number of issues with the move from BOOL to ggml_numa_strategies. Added a note about mirror mode note being implemented yet * Removing MIRROR_MODE code for this PR * Removing last bit of MIRROR_MODE code for this PR * Removing unneeded branch in server.cpp example and moving get_numa_affinity and making it static * Fixed lingering init_llama_backend() bool calls in tests and examples * Remote enum llama_numa_strategies * Revert bad merge with dynatemp flags * add missing enum ggml_numa_strategies declaration and revert sync problem with master * add missing enum ggml_numa_strategies declaration * fixed ggml_init_numa variable * Update ggml.h Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * Update READMEs with info about numa flags, change INTERLEAVE strategy name to DISTRIBUTE everywhere, implement the improved distribution strategy from @rankaiyx, fix a spelling mistake and un-merge some bad merges * split numa init out from llama_backend_init and created llama_numa_init. Updated all code paths and samples * Fix up some boolean vs enum comparisons * Added #ifdefs for non-Linux OS that don't have cpu_set_t datatype * Update ggml.h Align enum values Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml.c Remove whitespace Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml.c align paremeters Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update examples/server/server.cpp remove whitespace and align brace Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update common/common.cpp Remove whitespace and align brace Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * unified ggml_numa_strategy enum and fixed text alignment in server.cpp example * Update ggml.c simplified return for platforms without NUMA support Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * removed redundant else from cli argument processing of --numa * whitespace --------- Co-authored-by: root <root@nenya.lothlorien.ca> Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Author
Parents
  • common
    • File
      common.cpp
    • File
      common.h
  • examples
    • batched-bench
      • File
        batched-bench.cpp
    • batched.swift/Sources
      • File
        main.swift
    • batched
      • File
        batched.cpp
    • beam-search
      • File
        beam-search.cpp
    • embedding
      • File
        embedding.cpp
    • imatrix
      • File
        imatrix.cpp
    • infill
      • File
        infill.cpp
    • llama-bench
      • File
        llama-bench.cpp
    • llama.android/app/src/main/cpp
      • File
        llama-android.cpp
    • llama.swiftui/llama.cpp.swift
      • File
        LibLlama.swift
    • llava
      • File
        llava-cli.cpp
    • lookahead
      • File
        lookahead.cpp
    • lookup
      • File
        lookup.cpp
    • main
      • File
        README.md
      • File
        main.cpp
    • parallel
      • File
        parallel.cpp
    • passkey
      • File
        passkey.cpp
    • perplexity
      • File
        perplexity.cpp
    • quantize
      • File
        quantize.cpp
    • server
      • File
        README.md
      • File
        server.cpp
    • simple
      • File
        simple.cpp
    • speculative
      • File
        speculative.cpp
    • tokenize
      • File
        tokenize.cpp
  • File
    ggml.c
  • File
    ggml.h
  • File
    llama.cpp
  • File
    llama.h
  • tests
    • File
      test-autorelease.cpp
    • File
      test-model-load-cancel.cpp
    • File
      test-tokenizer-0-falcon.cpp
    • File
      test-tokenizer-0-llama.cpp
    • File
      test-tokenizer-1-bpe.cpp
    • File
      test-tokenizer-1-llama.cpp