Captum v0.3.1 ships fused DeepLIFT with ~7x speedup for same-size models
jmschreiber91 · x · 2026-10-26
Developer jmschreiber91 announced that a fused Cherimoya DeepLIFT implementation has been merged and released in Captum v0.3.1, delivering roughly 7x faster DeepLIFT for models of the same size (e.g. default 128 filters). This had been a major bottleneck even for lightweight models. The optimization came from a PR by @eugmattei.
More from Research
- EMNLP paper GENIE: a fine-grained metric locating where LLM stories are novel — gregd_nlp · 2026-10-27
- Hashed n-gram value embeddings push GPT to 3.2115 loss, beating 30M track record — RobertTLange · 2026-10-27
- MissionReport benchmark: frontier models score just ~60% on government status reporting — Exp_Mark · 2026-10-27
- TMLR paper: enforced thinking doesn't reliably make LLM agents disclose key info to users — SharonYixuanLi · 2026-10-27
- LLM-written Rust library bbtree verified: speed claims hold, memory savings reverse — lmoroney · 2026-10-27
- Diamandis: AI Cancer Navigator and $100 Genome Sequencing Close the Care Gap — PeterDiamandis · 2026-10-27