[Run Your Own] Running llama-swap as a proxy for llama.cpp on Guix

(define-public llama-swap
  (package
    (name "llama-swap")
    (version "228")
    (source
     (origin
       (method git-fetch)
       (uri (git-reference
              (url "https://github.com/mostlygeek/llama-swap")
              (commit (string-append "v" version))))
       (file-name (git-file-name name version))
       (sha256
        (base32 "1yxml6n4lyc8galm0q4jfxhlnhjkl2sbvsy2qzddc71rm90d7khh"))))
    (build-system go-build-system)
    (arguments
     (list
      #:tests? #f ;; TODO: Skip failing tests
      #:import-path "github.com/mostlygeek/llama-swap"
      #:phases
      #~(modify-phases %standard-phases
          ;; Force disable legacy ServeMux behaviour, with which routing
          ;; doesn't work.  It is enabled automatically because we use
          ;; GO111MODULE=off in go-build-system.
          (add-after 'unpack 'fix-httpmuxgo121
            (lambda _
              (substitute* "src/github.com/mostlygeek/llama-swap/llama-swap.go"
                (("^package main")
                 "//go:debug httpmuxgo121=0\n\npackage main")))))))
    (inputs (list go-github-com-stretchr-testify
                  go-github-com-shirou-gopsutil-v4
                  go-github-com-billziss-gh-golib
                  go-github-com-tidwall-gjson
                  go-github-com-tidwall-sjson
                  go-github-com-klauspost-compress
                  go-github-com-fxamacker-cbor-v2
                  go-gopkg-in-yaml-v3

                  go-github-com-gin-gonic-gin
                  go-github-com-charmbracelet-bubbles
                  go-github-com-charmbracelet-lipgloss
                  go-github-com-google-jsonschema-go))
    (home-page "https://github.com/mostlygeek/llama-swap")
    (synopsis "llama-swap")
    (description
     "llama-swap is an @code{OpenAI} API compatible server that gives you complete
control over how you use your hardware.  It automatically swaps to the
configuration of your choice for serving a model.  Since
@@url{https://github.com/ggerganov/llama.cpp/tree/master/examples/server,llama.cpp's
server} can't swap models, let's swap the server instead!")
    (license license:expat)))

(define (serialize-llama-cpp-configuration config)
  (match-record config <llama-cpp-configuration>
                (name huggingface-name parameters)
    (let ((llama-server-args (append (list "--port ${PORT}"
                                           (string-append "-hf " huggingface-name))
                                     parameters)))
      (format #f "  ~a:\n   cmd: llama-server ~a\n" name (string-join llama-server-args " ")))))

(define (llama-swap-config-file config)
  (match-record config <llama-swap-configuration>
                (llamas timeout log-to-stdout)
    (mixed-text-file "llama-swap-conf.yaml" "
healthCheckTimeout: " timeout "
logToStdout: " log-to-stdout "
models:
" (string-join (map serialize-llama-cpp-configuration llamas) ""))))

rodion@bumblebee-mighty ~$ cat /gnu/store/m3hpzgjyl66m01j1q8la2ddi0514q0l0-llama-swap-conf.yaml

healthCheckTimeout: 2400
logToStdout: both
models:
  qwen-3.5:
   cmd: llama-server --port ${PORT} -hf unsloth/Qwen3.5-27B-GGUF:UD-Q4_K_XL -c 64000 --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0.00
  qwen-3.6:
   cmd: llama-server --port ${PORT} -hf unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL -c 64000 --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0.00

(lambda args
  (when #$with-nvidia?
    (format #t "llama-cpp: running nvidia-modprobe~%")
    (system* #$(file-append nvidia-modprobe-package "/bin/nvidia-modprobe") "-c0" "-m")
    (format #t "llama-cpp: running nvidia-smi~%")
    (system* #$(file-append nvidia-driver-package "/bin/nvidia-smi"))
    (format #t "llama-cpp: waiting for nvidia devices~%")
    (let loop ((remaining 300))
      (cond
       ((every file-exists? nvidia-devices)
        (format #t "llama-cpp: nvidia devices ready~%"))
       ((zero? remaining)
        (error "llama-cpp: timed out waiting for nvidia devices"))
       (else
        (sleep 1)
        (loop (- remaining 1))))))
  (apply forkexec args))