DeepSeek V4.1 Flash pushed from broken to 284+ t/s on RTX PRO 6000, +78.7% over vLLM
SergioPaniego · x · 2026-11-20
Developer alvarobartt used Codex (GPT 6.1 Sol) usage credits to spend three days optimizing DeepSeek-V4.1-Flash on NVIDIA RTX PRO 6000 (sm120), going from not even starting on vLLM to 284+ tokens/s on HuggingFace Jobs instances — a 78.7% improvement over vLLM v0.32.0 with DSpark. All changes are open source, with a full article documenting the work.
More from coding & agent
- Claude drew an entire flyable game world with pure code — no images, no 3D models — prasenx · 2026-11-20
- Fixing mobile input auto-zoom: a Shadcn refinement workflow with Impeccable skills — bennash · 2026-11-20
- GTE-MLM sparse embedding models now natively supported in Transformers v5 — tomaarsen · 2026-11-20
- After evaluating Forge for MTG, researcher writes his own engine for RL agents — petrusenko_max · 2026-11-20
- Spring ecosystem ships 127 open-source releases in one day, led by Spring AI 2.1.0 — therealdanvega · 2026-11-20
- How to keep your Claude account from getting banned, according to one user's setup — huangyun_122 · 2026-11-20