Class: Gigatoken::CLI::Bench

Inherits:
Dry::CLI::Command
  • Object
show all
Defined in:
lib/gigatoken/cli/bench.rb

Overview

gigatoken bench TOKENIZER FILES... — measure encode throughput in MB/s and Mtok/s, mirroring upstream's Python CLI gigatoken bench output shape.

Instance Method Summary collapse

Instance Method Details

#call(tokenizer:, files:, doc_separator: nil, limit_bytes: "none", parallel: true, packed: false, pretokenizer: nil) ⇒ Object 



22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
 
# File 'lib/gigatoken/cli/bench.rb', line 22

def call(tokenizer:, files:, doc_separator: nil, limit_bytes: "none", parallel: true, packed: false, pretokenizer: nil, **)
  limit = Support.parse_size(limit_bytes)
  out.puts "#{label("cpu")}: #{Support.cpu_info}"

  gt_tokenizer = Support.load_tokenizer(tokenizer, pretokenizer: pretokenizer)

  start = Process.clock_gettime(Process::CLOCK_MONOTONIC)
  if packed
    encoded = gt_tokenizer.encode_files(Support.text_file_source(files, doc_separator), parallel: parallel, packed: true)
    n_bytes = files.sum { |file| File.size(file) }
    n_tokens = encoded.token_count
  elsif parallel
    docs = Support.subset_docs(Support.split_docs(files, doc_separator), limit)
    encoded = gt_tokenizer.encode_batch(docs)
    n_bytes = docs.sum(&:bytesize)
    n_tokens = encoded.sum(&:length)
  else
    encoded = gt_tokenizer.encode_files(Support.text_file_source(files, doc_separator), parallel: false)
    n_bytes = files.sum { |file| File.size(file) }
    n_tokens = encoded.sum(&:length)
  end
  seconds = Process.clock_gettime(Process::CLOCK_MONOTONIC) - start

  out.puts report("gigatoken", seconds, n_bytes, n_tokens)
rescue Gigatoken::Error => e
  err.puts "error: #{e.message}"
  exit(1)
end