-
-
Notifications
You must be signed in to change notification settings - Fork 197
Pull requests: dphnAI/aphrodite-engine
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix: gemma-4 inference with Pipeline Parallelism
#1663
opened May 1, 2026 by
AlpinDale
Collaborator
Loading…
[kernel][mobile] add mobile-optimized CPU backend
#1609
opened Nov 15, 2025 by
AlpinDale
Collaborator
Loading…
[kernel][moe] better splitK for fused moe
#1603
opened Nov 5, 2025 by
AlpinDale
Collaborator
Loading…
[API] feat: add reasoning recovery mechanism
#1541
opened Oct 3, 2025 by
AlpinDale
Collaborator
Loading…
[Build] feat: multi-backend build system to consolidate CUDA, ROCm, CPU, etc
#1540
opened Sep 29, 2025 by
AlpinDale
Collaborator
Loading…
[Kernel] feat: add NVFP4 blockwise MoE kernels for sm_120
#1528
opened Sep 23, 2025 by
AlpinDale
Collaborator
Loading…
feat(compilation): Extend sequence parallelism to activations
#1523
opened Sep 18, 2025 by
AlpinDale
Collaborator
Loading…
feat: overlap shared experts with send/recv
#1522
opened Sep 18, 2025 by
AlpinDale
Collaborator
Loading…
[Kernel][Quantization] feat: add Gluon kernels for AWQ quantization
#1520
opened Sep 17, 2025 by
AlpinDale
Collaborator
Loading…
fix: illegal memory access for FP8 MoE models in cutlass 3x grouped gemm kernel
#1446
opened Aug 28, 2025 by
AlpinDale
Collaborator
Loading…
fix: priority scheduler crashing in V1 scheduler under high load
#1445
opened Aug 27, 2025 by
AlpinDale
Collaborator
Loading…
[Kernel] feat: add custom CUDA kernels for all sampling ops
#1444
opened Aug 26, 2025 by
AlpinDale
Collaborator
Loading…
gguf: optimize prefill speeds for Q4_K quants
#1395
opened Jul 18, 2025 by
AlpinDale
Collaborator
Loading…
Fix metrics and allow disable block manager v2
#1299
opened Apr 15, 2025 by
Nero10578
Contributor
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2026-05-14.