Revision History
LLM inference engine · 6 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected a claim that NVIDIA set DeepSeek-R1 records in MLPerf Inference v5.0 (that round had no DeepSeek-R1 benchmark; NVIDIA's Blackwell results were on Llama 3.1 405B), and removed unsupported claims that EAGLE-3 is TensorRT-LLM's default speculator (plus 13 minor fixes)
Version 6 · Nov 5, 2026, 07:37 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:06 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:45 PM