main

GGitHubGeneralize dense-layer MLP hooks across interleaved MoE architectures (#1666)

5c44ea73创建于 8月14日历史提交

文件	最后提交记录	最后更新时间
adapter-creation-guide.md	Document all four adapter registration locations (#1514) * Document all adapter registration locations * Retrigger CI after notebook timeouts * Retry transient notebook timeouts * Retry CI after post-test hangs	2 个月前
adapter-specification.md	Generalize dense-layer MLP hooks across interleaved MoE architectures (#1666) * initial numerics fix * Additional clarification and bug cleanup * Fixing issues with MoE and Dense hooks * test cleanup and improvements	1 个月前
adapter-unit-test-guide.md		1 个月前
external-adapter-registration.md	Feat/external architecture registration (#1307) * feat: External architecture adapter registration and entry-point discovery * docs: External adapter registration guide with examples * test: ArchitectureAdapterFactory registration, selection, and entry-point tests * fix: Clarify matching requirement and add warnings for failed discovery * fix: Make register_adapter doctest self-contained with inline adapter class * fix: Address Copilot review - alias, loop isolation, test state leak * fix: Apply black formatting to factory file * fix: use select_architecture_adapter in register_adapter doctest * fix: guard native adapter override in discover_entry_points * test: drop TestSupportedArchitectures * test: add entry-point discovery tests * docs: document native adapter override prevention * fix: apply black formatting to test file * fix: handle None ep.dist in entry-point guard warning * fix: apply black formatting to factory file	3 个月前
hf-model-analysis-guide.md	Adding Architecture Adapter Creation Guide to Docs (#1274) * Adding architecture Adapter creation guide, add split QKV example to quantized LLaMA demo * ignore docs/build from black linting	4 个月前
hf-scraper.md	Updating the scraper to allow a single architecture scrape (#1360) * Updating the scraper to allow a single architecture scrape * Format checks	3 个月前