popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

wip -more responsive UI, better routing

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-08 09:07:54 +02:00
parent 518c259cd3
commit 3d82188dc1
14 changed files with 506 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.claude/memory/project-status.md
View File

@@ -46,3 +46,4 @@ Historical handoff note: `/mnt/c/Users/popov/Downloads/neuron-tai-alpha-handoff-
- Route hardening: tracker chat proxy and `/v1/route` diagnostics now use alias-aware preset node matching for split Qwen3.6 routes; dashboard derives grouped inference history from proxy route/complete console events and shows observed TPS after completion.
- Live proxy hardening: model lookup trims outer whitespace before alias matching (`qwen3.6-35b-a3b ` resolves), and tracker route logs/dashboard queue depth combine heartbeat queue with tracker-local proxy in-flight counts so Postman-style bursts no longer show every selected route as queue `0`.
- Split-shard streaming hardening: Qwen3.6-style distributed generation now emits SSE chunks token-by-token from the head node instead of buffering all generated text until completion. Tracker direct/relay stream proxy logs `proxy progress` with live tokens/TPS, dashboard Inference history shows currently processing requests with live TPS/tokens/queue, and relay stream completion no longer references an undefined `session_id`.
- Native Windows Qwen3.6-MoE import fix: `flash-linear-attention` imports `triton`; without `triton-windows`, startup fails with misleading `Could not import module 'Qwen3_5MoeForCausalLM'`. Installed `triton-windows` in `C:\Users\popov\miniforge3` and added it as a Windows-only node dependency.