Skip to content

Pull requests: dphnAI/sonar

New pull request New
50 Open 1,387 Closed
50 Open 1,387 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

Support for logit bias in specdec
#1717 opened Jul 23, 2026 by 50h100a Collaborator Loading…
[sync] vLLM 2026-07-21 — 867ff6973..8def3cdde
#1715 opened Jul 21, 2026 by AlpinDale Member Loading…
Don't disable other samplers for non-mirostat rows in a mixed batch
#1674 opened Jun 5, 2026 by lollinng Loading…
fix: gemma-4 inference with Pipeline Parallelism
#1663 opened May 1, 2026 by AlpinDale Member Loading…
2
[kernel][mobile] add mobile-optimized CPU backend
#1609 opened Nov 15, 2025 by AlpinDale Member Loading…
10
[kernel][moe] better splitK for fused moe
#1603 opened Nov 5, 2025 by AlpinDale Member Loading…
2
[kernel] feat: hybrid CPU-GPU MoE inference
#1550 opened Nov 2, 2025 by AlpinDale Member • Draft
Allow to force p2p
#1546 opened Oct 17, 2025 by Nero10578 Contributor Loading…
3
[API] feat: add reasoning recovery mechanism
#1541 opened Oct 3, 2025 by AlpinDale Member Loading…
6
[Build] feat: multi-backend build system to consolidate CUDA, ROCm, CPU, etc
#1540 opened Sep 29, 2025 by AlpinDale Member Loading…
5
[Build] fix: nvidia dockerfile issues
#1539 opened Sep 29, 2025 by AlpinDale Member Loading…
4
[Kernel] feat: add NVFP4 blockwise MoE kernels for sm_120
#1528 opened Sep 23, 2025 by AlpinDale Member Loading…
7
[Attention] feat: support PrefixLM
#1526 opened Sep 20, 2025 by AlpinDale Member Loading…
8
[Kernel][Comms] feat: add custom all-gather kernels
#1524 opened Sep 19, 2025 by AlpinDale Member • Draft
7
feat(compilation): Extend sequence parallelism to activations
#1523 opened Sep 18, 2025 by AlpinDale Member Loading…
3
feat: overlap shared experts with send/recv
#1522 opened Sep 18, 2025 by AlpinDale Member Loading…
4
[Kernel][Quantization] feat: add Gluon kernels for AWQ quantization
#1520 opened Sep 17, 2025 by AlpinDale Member Loading…
[Kernel] feat: sage attention support
#1513 opened Sep 12, 2025 by AlpinDale Member Loading…
fix: illegal memory access for FP8 MoE models in cutlass 3x grouped gemm kernel
#1446 opened Aug 28, 2025 by AlpinDale Member Loading…
fix: priority scheduler crashing in V1 scheduler under high load
#1445 opened Aug 27, 2025 by AlpinDale Member Loading…
[Kernel] feat: add custom CUDA kernels for all sampling ops
#1444 opened Aug 26, 2025 by AlpinDale Member Loading…
[Kernel][Experimental] feat: add Vulkan backend
#1416 opened Aug 14, 2025 by AlpinDale Member • Draft
2 of 11 tasks
[Kernel] feat: add Metal support for Apple Silicon GPU
#1415 opened Aug 12, 2025 by AlpinDale Member • Draft
5 of 11 tasks
[WIP] feat: ExLlamaV3 quantization format
#1398 opened Jul 22, 2025 by AlpinDale Member • Draft
gguf: optimize prefill speeds for Q4_K quants
#1395 opened Jul 18, 2025 by AlpinDale Member Loading…
ProTip! Exclude everything labeled bug with -label:bug.