Revision History
Continuous Batching · 8 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: Removed fabricated statistics (an invented Orca waste measurement, a 2.3x-4.3x vLLM-over-Orca figure, Sarathi-Serve latency numbers, TGI and TensorRT-LLM benchmark ranges, an SGLang-vs-vLLM range), fixed a composite NVIDIA quote, corrected TGI's history, SGLang's institutions and XQA's description, and updated stale TGI, TensorRT-LLM backend and Ollama status (plus 25 minor fixes)
Version 8 · Nov 2, 2026, 02:24 PM
- Improve internal links (2026-10-13)
Version 7 · Oct 13, 2026, 10:21 AM
- Correction: resolve forward-looking claims whose stated deadline had passed, re-anchor stale as-of statements, and fix related citation and figure errors found in the same pass
Version 6 · Aug 1, 2026, 11:52 AM
- Added 6 contextual internal links
Version 5 · Jul 23, 2026, 03:30 PM