SyslogSolution/syslog-harness
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Dashboard: GPU slot indicators show active/max concurrent requests. Koonimo API key added. Real-time queuing visibility.

Browse Source
This commit is contained in:
Abiba (pi)
2026-05-16 20:43:22 +00:00
parent bf90e57c5f
commit 654cdff718
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
router/router.py
+2 -1
View File
@@ -36,6 +36,7 @@ API_KEYS = {
"sk-syslog-tanko": {"tier": "enterprise", "agent": "Tanko"},
"sk-syslog-koby": {"tier": "enterprise", "agent": "Koby"},
"sk-syslog-kagenz0": {"tier": "enterprise", "agent": "Kagenz0"},
"sk-syslog-koonimo": {"tier": "enterprise", "agent": "Koonimo"},
"sk-starter-abc123": {"tier": "starter", "agent": "test-starter"},
"sk-professional-xyz789": {"tier": "professional", "agent": "test-pro"},
}
@@ -164,7 +165,7 @@ def get_metrics():
d = {"gpus":[],"route_counts":{},"agent_counts":{},"tier_counts":{},"recent":[],"timestamp":time.time(),"active_requests":{}}
for m in GPU_URLS:
h = check_gpu_health(m)
d["gpus"].append({"id":m,"gpu_name":h.get("gpu_name",m),"status":h.get("status"),"vram_used_mb":h.get("vram_used_mb"),"vram_total_mb":h.get("vram_total_mb"),"vram_pct":h.get("vram_pct"),"temp_c":h.get("temp_c"),"gpu_util_pct":h.get("gpu_util_pct"),"power_w":h.get("power_w"),"power_limit_w":h.get("power_limit_w"),"active_requests":gpu_active_count(m)})
d["gpus"].append({"id":m,"gpu_name":h.get("gpu_name",m),"status":h.get("status"),"vram_used_mb":h.get("vram_used_mb"),"vram_total_mb":h.get("vram_total_mb"),"vram_pct":h.get("vram_pct"),"temp_c":h.get("temp_c"),"gpu_util_pct":h.get("gpu_util_pct"),"power_w":h.get("power_w"),"power_limit_w":h.get("power_limit_w"),"active_requests":gpu_active_count(m), "max_concurrent": GPU_MAX_CONCURRENT.get(m, 1)})
d["active_requests"][m] = gpu_active_count(m)
if r:
try: