We have 2 of 9 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer Engine \nv{} recipe addresses this with current-tensor scaling, a randomized Hadamard transform (RHT), and bfloat16 (BF16) final layers, adding work outside the FP4 matr...
Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM. Standard speculative decoding is lossless: its rejection and resampling steps exactly preserve the LLM's sampling distribution. Recent work argues that r...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
