Skip to content

chore(db): clean up AgentX results #723

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cquil11 merged 2 commits into from
Aug 11, 2026
Merged

chore(db): clean up AgentX results #723

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
49b4be1
chore(db): purge unsupported AgentX model attempts
cquil11 Aug 11, 2026
d823952
chore(db): purge additional outdated AgentX attempts
cquil11 Aug 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions packages/db/src/etl/run-overrides.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,15 +92,21 @@ export const PURGED_RUN_ATTEMPTS: ReadonlyMap<number, ReadonlySet<number>> = new
[29413860950, new Set([3])], // 2026-07-16 | DeepSeek-V4 FP4 MI355X SGLang HiCache agentic | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[29445892486, new Set([2])], // 2026-07-16 | DeepSeek-V4 FP4 B200 vLLM agentic | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[29486959583, new Set([2])], // 2026-07-16 | DeepSeek-V4 FP4 B300 vLLM agentic | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[29506569772, new Set([2])], // 2026-07-16 | Kimi K2.5 FP4 B300 vLLM MTP agentic | Reason: AgentX is no longer supported for this model
[29651235293, new Set([1])], // 2026-08-07 | GLM-5.2 NVFP4 B300 SGLang single-node agentic | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[29657732517, new Set([1])], // 2026-07-18 | GLM-5.2 FP8 MI325X SGLang 1M agentic | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[29682242847, new Set([1])], // 2026-08-07 | GLM-5.2 NVFP4 B300 SGLang agentic HiCache | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[29706766201, new Set([5])], // 2026-07-21 | DeepSeek-V4 FP4 B300 vLLM LMCache agentic | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[29706772949, new Set([3])], // 2026-07-21 | DeepSeek-V4 FP4 B200 vLLM LMCache agentic | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[29765418393, new Set([5])], // 2026-07-20 | MiniMax M2.7 FP4 B200 SGLang MTP agentic | Reason: AgentX is no longer supported for this model
[29778042138, new Set([1])], // 2026-07-21 | DeepSeek-V4 FP4 B300 vLLM MTP agentic | Reason: Outdated AgentX harness; corrected by v1+ runs 31192604550 and 31415828111
[29778042858, new Set([2])], // 2026-07-22 | DeepSeek-V4 FP4 B200 vLLM MTP agentic | Reason: Outdated AgentX harness; corrected by v1+ run 31192602558
[30133534310, new Set([1])], // 2026-07-24 | GLM-5.2 FP8 H200 Dynamo-SGLang 1P2D agentic | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[30133535261, new Set([1])], // 2026-07-24 | GLM-5.2 FP8 H200 Dynamo-SGLang 2P2D agentic | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[30133570824, new Set([1])], // 2026-07-24 | GLM-5.2 FP8 H200 Dynamo-SGLang 2P4D agentic | Reason: Non MTP which we aren't focusing on for AgentX as well as outdated AgentX harness
[30231719317, new Set([1])], // 2026-07-27 | DeepSeek-V4 FP4 GB300 Dynamo-vLLM MTP agentic | Reason: Outdated AgentX harness
[30391410523, new Set([1])], // 2026-07-30 | Qwen3.5 FP4 GB300 Dynamo-SGLang MTP agentic | Reason: Outdated AgentX harness; corrected by v1+ run 31042542308
[30425131777, new Set([3])], // 2026-07-30 | Kimi K3 FP4 B300 vLLM MTP agentic | Reason: Outdated AgentX harness
]);

export interface BenchmarkPointKey {
Expand Down