Ilker ManapandClaude Opus 5.5 1908bfb4b2 Strata on cuda01 end to end: its engine is the shard's, its metrics read ...

Found running it through the cluster:

- Strata's server starts its engine in a process group of its own, so the
  agent saw a GPU replica on the CPU and its 22 GB as somebody else's
  memory. A process the shard started, at any remove, is now the shard's.
- An adopted shard's kept compute was sent at once and never again, so a
  wrong one read again on adoption never reached the control plane: what
  is sent is sent again when it changes, and a GPU shard kept as the CPU
  is read again on adoption.
- /metrics/prometheus is llama.cpp's names without the KV cache; vLLM's,
  with it, are /metrics?format=prometheus. The router now sees running 1,
  waiting 2 under load.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-29 15:48:15 +01:00

..

llamacpp_test.go

Wait for what tests check instead of sleeping and hoping

2026-09-30 01:36:55 +02:00

parse_test.go

Phase 1 (1/2): scheduler pipeline, endpoint registry, metric scraping

2026-09-16 01:15:21 +02:00

parse.go

Strata on cuda01 end to end: its engine is the shard's, its metrics read

2026-10-29 15:48:15 +01:00

poller.go

Pictures from ComfyUI at /v1/images/generations

2026-10-09 21:15:50 +02:00

sglang_test.go

SGLang read in its own metric names, started serving them, and asked for its own help

2026-10-05 00:20:25 +02:00

strata_test.go

Strata on cuda01 end to end: its engine is the shard's, its metrics read

2026-10-29 15:48:15 +01:00

trtllm_test.go

TensorRT-LLM as an engine, and models from Ollama into the mirror

2026-10-05 00:02:01 +02:00