Adds a committed .gitattributes so Windows and Linux checkouts converge
on LF for all text files, overriding each developer's local core.autocrlf.
Renormalizes existing blobs (server.py, dashboard.html, etc.) that had
CRLF baked in, clearing the repo-wide phantom "modified" churn.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Bump the node package's transformers floor to 5.12 (older versions lack
composite Qwen3_5MoeConfig handling and fail with missing vocab_size), and
explain in QUICKSTART/INSTALL_WINDOWS that the flash-linear-attention /
causal-conv1d fast-path warning is a harmless CPU fallback.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Qwen3.5/3.6-MoE checkpoints ship vision (model.visual.*) and multi-token-
prediction (mtp.*) weights; the partial shard loader assigned them into the
text-only Qwen3_5MoeForCausalLM and crashed with AttributeError 'mtp'.
Filter selected tensors against the built model's state_dict keys, matching
transformers' _keys_to_ignore_on_load_unexpected behavior.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Start background re-registration when the tracker is unreachable at startup so nodes do not stay permanently unregistered.
Co-authored-by: Cursor <cursoragent@cursor.com>
Unify --model and --model-id so catalog names use the tracker path, and allow --shard-start/--shard-end with --model instead of requiring --model-id.
Co-authored-by: Cursor <cursoragent@cursor.com>
Resolve conflicts in dashboard.html (Call wall + live TPS/queue from remote) and server.py (proxy progress logging, request id forwarding, current_requests on node entries).
Co-authored-by: Cursor <cursoragent@cursor.com>
- cli.py: change default --quantization from bfloat16 to int8; saves
~50% VRAM/RAM for new nodes that don't specify a quantization
- startup.py: display memory budget and GPU info in GB (e.g. 124.9 GB RAM)
instead of MB; show remaining headroom after full model load
- test_tracker_routing.py: add test_shard_heal_cycle_surviving_node_covers_dead_peers_gap
— end-to-end proof that:
1. tracker purges expired node A and queues LOAD_SHARD for node B
2. node B receives directive on next heartbeat
3. TorchNodeServer.apply_tracker_directives hot-swaps the backend
4. node B re-registers covering the full model; coverage gap closed
Test runs in <1s with monkeypatched _load_backend (no GPU needed)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Nodes behind NAT (5G, WSL2, home routers) can now participate in
distributed pipeline inference over the internet via the relay server.
- torch_server: add module-level _relay_hop() that opens a WebSocket
to relay.../rpc/{peer_id}, sends the binary activation with
body_base64 encoding, and returns (status, headers, body)
- torch_server: _get_remaining_route returns list[dict] (was list[tuple])
preserving relay_addr from injected X-Meshnet-Route header and
from /v1/route slow-path node info
- torch_server: _run_downstream_pipeline dispatches via _relay_hop
when hop has relay_addr; falls back to direct HTTP on relay error
- tracker server: downstream_hops dicts include relay_addr when node
has one registered, so head node knows how to reach each peer
- relay_bridge: binary bodies (bfloat16 activations) use body_base64;
response preserves all X-Meshnet-* headers
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
