profile: optimize Parse allocs

[pymq]

go test -bench='^\QBenchmarkParse\E$' -run='^$' -count=10 -benchtime=5s

goos: linux
goarch: amd64
pkg: github.com/google/pprof/profile
cpu: 13th Gen Intel(R) Core(TM) i7-1360P
         │ old-parse.txt │            new-parse.txt             │
         │    sec/op     │    sec/op     vs base                │
Parse-16    62.07m ± 13%   55.54m ± 13%  -10.52% (p=0.035 n=10)

         │ old-parse.txt │            new-parse.txt             │
         │     B/op      │     B/op      vs base                │
Parse-16    47.56Mi ± 0%   41.09Mi ± 0%  -13.59% (p=0.000 n=10)

         │ old-parse.txt │            new-parse.txt            │
         │   allocs/op   │  allocs/op   vs base                │
Parse-16     272.9k ± 0%   175.8k ± 0%  -35.58% (p=0.000 n=10)

[aalexand]

nit: Can this be written a bit shorter as

func peekNumVarints(data []byte) int {
	for numVarints := 0; len(data) > 0; numVarints++ {
		var err error
		if _, data, err = decodeVarint(data); err != nil {
			break
		}
	}
	return numVarints
}