Ilker ManapandClaude Opus 5.5
f4b34dbf11
CI / test (push) Successful in 9m37s
FreeToken (FlashML-org/FreeToken) serves mixture-of-experts models several times a card's size from one card, experts in RAM, from Hugging Face safetensors checkpoints. Installed like vLLM, from PyPI by uv, on every node it runs on: compute capability 8.0+, driver 580+, x86-64, and the CUDA 13 toolkit it compiles kernels with. Older cards are passed over: on cuda01's Quadro RTX 6000 (7.5) 0.2.1 had no kernel image for the first prefill, and in fp16 hit an illegal memory access on its first request. ft serve gets the model, address, card and served name; the key goes in FREETOKEN_API_KEY. Flags that read files or fetch are refused, as are FREETOKEN_ variables naming paths or the agent's own settings. ctl model context sets --max-seq-len-override. Readiness now also waits for an engine whose /health answers 200 while its body says "loading", as FreeToken's does from the moment its HTTP server is up. FreeToken is followed release by release: a weekly workflow fails when PyPI has a version newer than DefaultEngines installs (scripts/engine_releases.py). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
94 lines
2.6 KiB
Go
94 lines
2.6 KiB
Go
package discovery
|
|
|
|
import (
|
|
"encoding/json"
|
|
"os"
|
|
"os/exec"
|
|
"path/filepath"
|
|
"regexp"
|
|
"slices"
|
|
"strconv"
|
|
"strings"
|
|
)
|
|
|
|
// CUDAToolkit is the root of an installed CUDA toolkit of this major version
|
|
// — the directory whose bin holds nvcc — or "" when there is none. Engines
|
|
// that compile their kernels where they run (FreeToken, ComfyUI's compiled
|
|
// nodes) need one matching the CUDA their torch was built for, and a
|
|
// toolkit of another major version compiles code that torch cannot load.
|
|
//
|
|
// CUDA_HOME is looked at first, then /usr/local/cuda, then every
|
|
// /usr/local/cuda-<version>, newest first.
|
|
func CUDAToolkit(major int) string {
|
|
return cudaToolkitIn(major, os.Getenv("CUDA_HOME"), "/usr/local")
|
|
}
|
|
|
|
func cudaToolkitIn(major int, home, root string) string {
|
|
var dirs []string
|
|
if home != "" {
|
|
dirs = append(dirs, home)
|
|
}
|
|
dirs = append(dirs, filepath.Join(root, "cuda"))
|
|
versioned, _ := filepath.Glob(filepath.Join(root, "cuda-*"))
|
|
slices.SortFunc(versioned, func(a, b string) int { return versionCompare(b, a) })
|
|
dirs = append(dirs, versioned...)
|
|
for _, d := range dirs {
|
|
if _, err := os.Stat(filepath.Join(d, "bin", "nvcc")); err != nil {
|
|
continue
|
|
}
|
|
if toolkitMajor(d) == major {
|
|
return d
|
|
}
|
|
}
|
|
return ""
|
|
}
|
|
|
|
// toolkitMajor is a toolkit's major version, from the version.json every
|
|
// toolkit since 11.1 carries, or from nvcc where it has none; 0 when neither
|
|
// says.
|
|
func toolkitMajor(dir string) int {
|
|
if b, err := os.ReadFile(filepath.Join(dir, "version.json")); err == nil { //nolint:gosec // a toolkit's own file
|
|
var v struct {
|
|
CUDA struct {
|
|
Version string `json:"version"`
|
|
} `json:"cuda"`
|
|
}
|
|
if json.Unmarshal(b, &v) == nil && v.CUDA.Version != "" {
|
|
n, _ := strconv.Atoi(strings.SplitN(v.CUDA.Version, ".", 2)[0])
|
|
return n
|
|
}
|
|
}
|
|
//nolint:gosec // nvcc of a toolkit found on disk
|
|
out, err := exec.Command(filepath.Join(dir, "bin", "nvcc"), "--version").Output()
|
|
if err != nil {
|
|
return 0
|
|
}
|
|
if m := nvccRelease.FindSubmatch(out); m != nil {
|
|
n, _ := strconv.Atoi(string(m[1]))
|
|
return n
|
|
}
|
|
return 0
|
|
}
|
|
|
|
var nvccRelease = regexp.MustCompile(`release (\d+)\.`)
|
|
|
|
// versionCompare orders two paths ending in dotted versions: cuda-13.10 is
|
|
// newer than cuda-13.4, which comparing them as text gets wrong.
|
|
func versionCompare(a, b string) int {
|
|
pa := strings.Split(strings.TrimPrefix(filepath.Base(a), "cuda-"), ".")
|
|
pb := strings.Split(strings.TrimPrefix(filepath.Base(b), "cuda-"), ".")
|
|
for i := range max(len(pa), len(pb)) {
|
|
var x, y int
|
|
if i < len(pa) {
|
|
x, _ = strconv.Atoi(pa[i])
|
|
}
|
|
if i < len(pb) {
|
|
y, _ = strconv.Atoi(pb[i])
|
|
}
|
|
if x != y {
|
|
return x - y
|
|
}
|
|
}
|
|
return 0
|
|
}
|