Skip to content

Pull requests: turboderp-org/exllamav3

New pull request New
11 Open 82 Closed
11 Open 82 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

Tensor-parallel support for the CPU page cache tier
#268 opened Jul 30, 2026 by pdcruze Loading…
Cache statistics for production sizing (Generator.get_cache_stats)
#267 opened Jul 30, 2026 by pdcruze Loading…
Asynchronous recurrent tail stashing
#266 opened Jul 30, 2026 by pdcruze • Draft
Page-aligned recurrent tail checkpoints on completion
#265 opened Jul 30, 2026 by pdcruze Loading…
Exclude multimodal-dependent pages from the CPU cache tier
#264 opened Jul 30, 2026 by pdcruze Loading…
1
Allow using multiple draft models at once
#261 opened Jul 28, 2026 by Ednaordinary • Draft
2 of 5 tasks
Add Gemma4 E4B and E2B support (per-layer embeddings, cross-layer KV sharing)
#253 opened Jul 25, 2026 by pdcruze Loading…
Cache/Attn: Load Q8 cache bytes directly
#247 opened Jul 18, 2026 by remichu-ai Contributor Loading…
[kernel] Persistent route-packed (route_block x n_tile) schedule for exl3 fused MoE (sm120)
#246 opened Jul 15, 2026 by brandonmmusic-max Loading…
2
fix(security): 2 improvements across 2 files
#214 opened May 24, 2026 by tomaioo Loading…
Detailed size estimation + fix #193 (overestimating fused QKV storage)
#194 opened Apr 16, 2026 by mratsim Contributor Loading…
1
1
ProTip! Updated in the last three days: updated:>2026-07-27.