Ilker ManapandClaude Opus 5.5 25b3e129fe What a shard computes on survives the agent's and the control plane's restarts ...

It was sent once, with READY, and kept only in the leader's memory: a
failover or an agent restart lost it. The agent now keeps it with the
shard's state on disk (ShardSpec.Compute, set by Supervisor.SetCompute) and
reports it with each running shard when it registers (RunningShard.compute),
which adoption carries onto the replica.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-10-07 13:51:40 +02:00

..

compute_test.go

A replica says what its engine computes on, and llama.cpp's word on the CPU refuses a GPU placement

2026-10-07 13:02:17 +02:00

compute.go

A replica says what its engine computes on, and llama.cpp's word on the CPU refuses a GPU placement

2026-10-07 13:02:17 +02:00

engine.go

What a shard computes on survives the agent's and the control plane's restarts

2026-10-07 13:51:40 +02:00

engines_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

kvevents_test.go

Precise KV-index routing: vLLM KV cache events through the agent, routed by leading blocks held

2026-10-05 01:21:11 +02:00

llamacpp_test.go

Serve vision models with their projector and original weights on vLLM; group the mirror by version

2026-10-04 00:42:59 +02:00

llamacpp.go

engine-check computes a token on the GPU, and finds the installed llama.cpp

2026-10-07 13:04:38 +02:00

lora_test.go

LoRA adapters on vLLM, loaded on demand with replica affinity: max_loaded_adapters

2026-10-05 01:14:38 +02:00

lora.go

LoRA adapters on vLLM, loaded on demand with replica affinity: max_loaded_adapters

2026-10-05 01:14:38 +02:00

mig_test.go

MIG: a card in MIG mode is placed as its instances, each a GPU of class <card>-mig-<profile>

2026-10-05 00:01:14 +02:00

probe_test.go

Stop placing engines on nodes that do not have them

2026-09-27 16:11:55 +02:00

probe.go

Install vLLM on every GPU node that can run it, as llama.cpp is

2026-09-29 13:15:54 +02:00

sglang.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

sim_test.go

Onboard a node with a script, and find two examples that never worked

2026-09-16 12:28:36 +02:00

sim.go

Have engines listen on the management address, and take SGLang's key off its command line

2026-10-04 10:36:42 +02:00

trtllm_test.go

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

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

trtllm.go

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

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

unsafeenv_test.go

Refuse profile env and args that would run code or touch files on the nodes

2026-10-04 09:54:45 +02:00

unsafeenv.go

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

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

vllm.go

Merge C24 KV-index routing from vLLM's cache events

2026-10-05 01:24:25 +02:00