Skip to content

Pull requests: turboderp-org/exllamav3

New pull request New
8 Open 33 Closed
8 Open 33 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

nanochat: value embeddings, residual scalars, backout
#173 opened Mar 23, 2026 by Katehuuh Loading…
fix(formatron): handle duplicate BPE token IDs and kbnf mask/accept inconsistency
#170 opened Mar 16, 2026 by lesj0610 Loading…
Allow explicit compatibility tensor dtype casts
#167 opened Mar 7, 2026 by lesj0610 Loading…
Support alternate 2D linear checkpoint layouts
#166 opened Mar 7, 2026 by lesj0610 Loading…
test(eval): add flashinfer regression and benchmark coverage
#157 opened Mar 2, 2026 by lesj0610 Loading…
1
feat(deepseek): add DeepSeek MLA and VL2 support
#158 opened Mar 2, 2026 by lesj0610 Loading…
1
feat(attn): add switchable flash-attn and flashinfer backends
#156 opened Mar 2, 2026 by lesj0610 Loading…
1
Switch ExLlamaV3 to flashinfer and add MLA/Qwen3.5 support
#152 opened Feb 25, 2026 by lesj0610 Loading…
9
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.