Ilker ManapandClaude Opus 5.5
62657f4c2a
CPU replicas start on half the machine's CPUs, not all of them: two busy llama.cpp servers each spinning on all 8 vCPUs fell to 0.8 tok/s apiece, where at 4 threads they keep 5.5. llamacpp.threads sets it per node. Inference requests can be traced over OTLP/HTTP (tracing.endpoint), with admission, schedule and upstream spans and traceparent sent to the engine. Security: onboarding no longer puts the cluster root in the system trust store and removes it where it was; the mirror's mutual-TLS API can be limited to named certificates (--api-client); init.log no longer keeps the administrator's password; a warning when auth is off on a public listen; the recorded actor is sanitised and sudo-aware; Ray's dashboard is off, and the remaining engine gaps are documented. reconciler.go and agent.go are split by topic, the status mapping of each failure is tested, and the plan's checklist is brought up to date. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
86 lines
3.7 KiB
AMPL
86 lines
3.7 KiB
AMPL
module gitea.mynodes.xyz/ilker/llmgw
|
|
|
|
go 1.26.3
|
|
|
|
require (
|
|
connectrpc.com/connect v1.21.0
|
|
github.com/NVIDIA/go-nvml v0.13.4-0
|
|
github.com/cespare/xxhash/v2 v2.3.0
|
|
github.com/charmbracelet/bubbletea v1.3.10
|
|
github.com/charmbracelet/lipgloss v1.1.0
|
|
github.com/jackc/pgx/v5 v5.11.0
|
|
github.com/knadh/koanf/parsers/yaml v1.1.1
|
|
github.com/knadh/koanf/providers/env/v2 v2.0.1
|
|
github.com/knadh/koanf/providers/file v1.2.1
|
|
github.com/knadh/koanf/v2 v2.3.6
|
|
github.com/mattn/go-isatty v0.0.24
|
|
github.com/prometheus/client_golang v1.24.1
|
|
github.com/prometheus/client_model v0.6.3
|
|
github.com/prometheus/common v0.71.0
|
|
github.com/spf13/cobra v1.10.2
|
|
github.com/yuin/goldmark v1.8.6
|
|
go.opentelemetry.io/otel v1.46.0
|
|
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.46.0
|
|
go.opentelemetry.io/otel/sdk v1.46.0
|
|
go.opentelemetry.io/otel/trace v1.46.0
|
|
golang.org/x/crypto v0.57.0
|
|
golang.org/x/net v0.59.0
|
|
golang.org/x/sync v0.23.0
|
|
google.golang.org/protobuf v1.36.12
|
|
modernc.org/sqlite v1.59.0
|
|
)
|
|
|
|
require (
|
|
github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect
|
|
github.com/beorn7/perks v1.0.1 // indirect
|
|
github.com/cenkalti/backoff/v5 v5.0.3 // indirect
|
|
github.com/charmbracelet/colorprofile v0.4.1 // indirect
|
|
github.com/charmbracelet/x/ansi v0.11.6 // indirect
|
|
github.com/charmbracelet/x/cellbuf v0.0.15 // indirect
|
|
github.com/charmbracelet/x/term v0.2.2 // indirect
|
|
github.com/clipperhouse/displaywidth v0.9.0 // indirect
|
|
github.com/clipperhouse/stringish v0.1.1 // indirect
|
|
github.com/clipperhouse/uax29/v2 v2.5.0 // indirect
|
|
github.com/dustin/go-humanize v1.0.1 // indirect
|
|
github.com/erikgeiser/coninput v0.0.0-20211004153227-1c3628e74d0f // indirect
|
|
github.com/fsnotify/fsnotify v1.9.0 // indirect
|
|
github.com/go-logr/logr v1.4.4 // indirect
|
|
github.com/go-logr/stdr v1.2.2 // indirect
|
|
github.com/go-viper/mapstructure/v2 v2.5.0 // indirect
|
|
github.com/google/uuid v1.6.0 // indirect
|
|
github.com/grpc-ecosystem/grpc-gateway/v2 v2.30.0 // indirect
|
|
github.com/inconshreveable/mousetrap v1.1.0 // indirect
|
|
github.com/jackc/pgpassfile v1.0.0 // indirect
|
|
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
|
|
github.com/jackc/puddle/v2 v2.2.2 // indirect
|
|
github.com/knadh/koanf/maps v0.1.2 // indirect
|
|
github.com/lucasb-eyer/go-colorful v1.3.0 // indirect
|
|
github.com/mattn/go-localereader v0.0.1 // indirect
|
|
github.com/mattn/go-runewidth v0.0.19 // indirect
|
|
github.com/mitchellh/copystructure v1.2.0 // indirect
|
|
github.com/mitchellh/reflectwalk v1.0.2 // indirect
|
|
github.com/muesli/ansi v0.0.0-20230316100256-276c6243b2f6 // indirect
|
|
github.com/muesli/cancelreader v0.2.2 // indirect
|
|
github.com/muesli/termenv v0.16.0 // indirect
|
|
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
|
|
github.com/ncruces/go-strftime v1.0.0 // indirect
|
|
github.com/prometheus/procfs v0.21.1 // indirect
|
|
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
|
|
github.com/rivo/uniseg v0.4.7 // indirect
|
|
github.com/spf13/pflag v1.0.9 // indirect
|
|
github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e // indirect
|
|
go.opentelemetry.io/auto/sdk v1.2.1 // indirect
|
|
go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.46.0 // indirect
|
|
go.opentelemetry.io/otel/metric v1.46.0 // indirect
|
|
go.opentelemetry.io/proto/otlp v1.11.0 // indirect
|
|
go.yaml.in/yaml/v3 v3.0.5 // indirect
|
|
golang.org/x/sys v0.48.0 // indirect
|
|
golang.org/x/text v0.42.0 // indirect
|
|
google.golang.org/genproto/googleapis/api v0.0.0-20260819154853-08b0e4226688 // indirect
|
|
google.golang.org/genproto/googleapis/rpc v0.0.0-20260819154853-08b0e4226688 // indirect
|
|
google.golang.org/grpc v1.83.1 // indirect
|
|
modernc.org/libc v1.75.7 // indirect
|
|
modernc.org/mathutil v1.7.1 // indirect
|
|
modernc.org/memory v1.12.1 // indirect
|
|
)
|