Skip to content

Pull requests: lightseekorg/tokenspeed

New pull request New
42 Open 802 Closed
42 Open 802 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

refactor(kernel): organize amd gluon kernels based on generations
#880 opened Aug 1, 2026 by borontion Contributor Loading…
1
[WIP](perf): Optimize Kimi K3 MoE input projections and low-token decode
#878 opened Jul 31, 2026 by panditsa Contributor Loading…
3
feat(amd): add initial GFX1250 Gluon MLA kernels
#877 opened Jul 31, 2026 by Yu-Zhewen Contributor Loading…
7
fix(kimi-k3): serve on GB200 -- LCM packing, layer derivation, kda la…
#876 opened Jul 31, 2026 by nperrin-fr Collaborator • Draft
3
feat: improve multi-node usability
#873 opened Jul 31, 2026 by syuoni Member Loading…
9
feat(DeepEP): support fp8 deepep path
#872 opened Jul 31, 2026 by tuanzhangCS Contributor Loading…
2
deps: bump TRTLLM kernel to 20260731
#870 opened Jul 31, 2026 by Xiangyi1996 Collaborator • Draft
feat: add Qwen2.5-MoE model support
#866 opened Jul 31, 2026 by potoior Loading…
8
refactor(mla): make K2.5 and GLM5.2 compatible with flatkv
#865 opened Jul 31, 2026 by yweng0828 Contributor • Draft
Remove Radix cache path and consolidate runtime cache handling
#864 opened Jul 31, 2026 by wangbo981016 Contributor Loading…
43
Support detailed token logprobs for RL and distillation
#861 opened Jul 31, 2026 by HJSang Collaborator Loading…
10
perf(comm): MNNVL fused all-reduce (one-shot + two-shot) for cross-node TP
#860 opened Jul 31, 2026 by nperrin-fr Collaborator Loading…
16
[WIP] perf(kda): CuTe DSL fused decode for KDA linear attention
#857 opened Jul 30, 2026 by nperrin-fr Collaborator • Draft
1
fix(runtime): reject ambiguous prompt sources
#854 opened Jul 30, 2026 by ShiroKSH Loading…
fix(spec): revert dflash-specific branches in speculative runtime
#853 opened Jul 30, 2026 by minedec Contributor • Draft
perf(kimi-k3): fuse AMD native MoE up projection epilogue
#841 opened Jul 29, 2026 by qedawkins Contributor Loading…
1
perf: fuse MiniMax sparse cache insertion
#839 opened Jul 29, 2026 by FlamingoPg Contributor • Draft
[WIP] perf(kimi3): retile warp decode
#831 opened Jul 28, 2026 by panditsa Contributor Loading…
2
feat(dspark): Add DSpark support
#829 opened Jul 28, 2026 by minedec Contributor • Draft
2
feat(qwen3.5): support text-only qwen3.5 checkpoint config
#828 opened Jul 28, 2026 by minedec Contributor • Draft
fix(runtime): keep multimodal tensors inline across nodes
#826 opened Jul 28, 2026 by tuanzhangCS Contributor • Draft
2
feat: wire flashinfer autotuner
#820 opened Jul 27, 2026 by syuoni Member Loading…
5
deps: test TensorRT-LLM rc22 kernel wheel
#818 opened Jul 27, 2026 by Xiangyi1996 Collaborator • Draft
2
feat: support torchspec training
#798 opened Jul 25, 2026 by Dogacel Contributor Loading…
4
feat(kernel): support small-batch Gluon MLA decode
#793 opened Jul 24, 2026 by Max191 Contributor Loading…
6
ProTip! Type g i on any issue or pull request to go back to the issue listing page.