This website requires JavaScript.
Explore
Help
Register
Sign In
abiba-bot
0 Followers
·
0 Following
Joined on
2026-05-16
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues.
Learn more about blocking a user.
User to block:
Optional note:
The note is not visible to the blocked user.
Cancel
Block
Repositories
1
Projects
Packages
Public Activity
Starred Repositories
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-30 13:15:20 +00:00
060a47fce9
revert: MoE back to 2 slots (cross-agent spread now prevents hotspot)
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-30 12:55:31 +00:00
34fb7516e1
fix: cross-agent GPU spreading prevents hotspot hammering
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-30 12:52:25 +00:00
acbcb20837
fix: MoE concurrency 2→1 (95C thermal emergency)
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-29 09:45:45 +00:00
a3bca93d9b
fix: buffer SSE chunks for large streaming responses
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-28 21:45:24 +00:00
d53685d874
feat: agent-aware GPU load balancing
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-28 21:40:20 +00:00
54a4f26db7
fix: Default tier back to Dense-first (MoE overheating at 91°C)
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-27 07:22:32 +00:00
fb1d51b93b
restructure: routing prioritized by reasoning requirements
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-27 07:16:01 +00:00
9a0d69ce8d
feat: Dense 128K context + 2 slots, VLM second in Heavy tier
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-27 00:29:27 +00:00
621a897bec
tune: raise Tier 2 threshold 4K→10K tok, 6→10 turns for VLM
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-27 00:04:43 +00:00
93d0d3cc4b
revert: MoE concurrency back to 2 (Dense-first routing handles thermal)
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-27 00:01:34 +00:00
c4ea5e3a98
fix: flip Tier 4 (Heavy) to Dense-first for thermal safety
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-26 23:47:09 +00:00
ebe8f9ced4
fix: reduce MoE concurrency 2→1 to prevent thermal timeout (94°C)
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-26 22:00:22 +00:00
b3db0841ef
feat: redesigned routing tiers for even GPU distribution + speed priority
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-26 12:37:54 +00:00
80362fa528
fix: default performance window to 24h so all models appear immediately
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-26 12:31:55 +00:00
7ef9e58f61
fix: restore /api/performance route in dashboard (was overwritten to /api/timeseries)
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-26 12:18:33 +00:00
f47c3f3304
feat: latency vs prompt size scatter plot on dashboard
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-25 19:58:54 +00:00
cfb05fa501
feat: capture streaming token counts from SSE final chunk
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-25 19:45:24 +00:00
b2ec4b0572
fix: throughput panel handles streaming-only models gracefully
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-25 17:00:42 +00:00
8c5c922a4e
fix: handle single data point in performance percentiles
abiba-bot
pushed to
main
at
abiba-bot/inference-harness
2026-05-25 16:58:17 +00:00
f42747d721
feat: performance analytics panel on dashboard
Previous
1
Next
