Search results

Llama-3.1-8B inference time with different batch sizes

Status: Open.

#2386 In mlcommons/inference;

· mahmoodn opened on Nov 5, 2025

[Llama2-70] No matching distribution found for torch==2.2.0.dev20231006+cpu

Status: Open.

#2380 In mlcommons/inference;

· mahmoodn opened on Oct 27, 2025

Define standard for representing and filtering heterogeneous systems on the official result table

Status: Open.

#2379 In mlcommons/inference;

· rausavar opened on Oct 24, 2025

Increase expected QPS so the loadgen pre-generates a larger (coalesced) query

Status: Open.

#2375 In mlcommons/inference;

· jinz2014 opened on Oct 22, 2025

Documenting the behaviors of various config arguments in mlperf.conf and user.conf

Status: Open.

#2356 In mlcommons/inference;

· anandhu-eng opened on Oct 7, 2025

Bandwidth Requirement check in submission checker

postmortem 5.1

Status: Open.

#2347 In mlcommons/inference;

· arjunsuresh opened on Sep 30, 2025

Proposing the change of <code>closed/participant_name/code/</code> to <code>closed/participant_name/src</code>

Status: Open.

#2346 In mlcommons/inference;

· v-shobhit opened on Sep 29, 2025

Not able to cross 2000 Samples/second for RGAT inferencing on tiny dataset

Status: Open.

#2342 In mlcommons/inference;

· adeepak7 opened on Sep 24, 2025

[BUG] Llama 3.1 8b Server and SingleStream Scenario fail

Status: Open.

#2341 In mlcommons/inference;

· catan2001 opened on Sep 18, 2025

R-GAT Offline Test failed with file not found in the dataset directory

Status: Open.

#2329 In mlcommons/inference;

· arjunsuresh opened on Sep 2, 2025

Request to reduce size of LLM checkpoints hosted by MLCommons

Status: Open.

#2323 In mlcommons/inference;

· tianmu-li opened on Aug 13, 2025

Revisit Early stopping

Status: Open.

#2322 In mlcommons/inference;

· uday-at-broadcom opened on Aug 13, 2025