Skip to content

Pull requests: lightseekorg/tokenspeed

New pull request New
36 Open 440 Closed
36 Open 440 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

feat(kernel): Tie weight preprocessors to kernels
#480 opened Jun 18, 2026 by Max191 Contributor Loading…
Add AMD Kimi MXFP4 CI job
#476 opened Jun 18, 2026 by qedawkins Contributor Loading…
13
feat(dflash): Add DFlash support
#472 opened Jun 18, 2026 by yweng0828 Contributor Loading…
9
test(agentic): add EvalScope trie benchmark protocol
#466 opened Jun 17, 2026 by Xiangyi1996 Collaborator • Draft
test(ci): add DeepSeek-V4-Flash MTP AIME25 eval
#461 opened Jun 16, 2026 by dongjiyingdjy Contributor Loading…
2
perf(kernel): optimize Qwen vision QKV rotary layout
#456 opened Jun 15, 2026 by qimcis Contributor Loading…
7
fix(scheduler): release paged-cache snapshots in ~HybridPrefixCache to avoid teardown use-after-free
#455 opened Jun 15, 2026 by Sunt-ing Loading…
test: add dp4ep4 case in CI
#453 opened Jun 15, 2026 by tuanzhangCS Contributor • Draft
4
[WIP] Refactor Cache Management
#447 opened Jun 15, 2026 by wangbo981016 Contributor • Draft
[WIP] EPD: encode-worker path, async embedding receive, E2P row-sharding
#437 opened Jun 12, 2026 by chenht2022 Contributor • Draft
Fix EP8 DP/TP RSAG init and empty LM head
#416 opened Jun 11, 2026 by yubofredwang Contributor Loading…
2
Port mamba2 kernels and runtime from sglang#03c77dc
#412 opened Jun 10, 2026 by netanel-haber Loading…
3
[WIP] feat(config): runtime config decoupling(design for reference)
#383 opened Jun 8, 2026 by rjzhb Collaborator • Draft
perf(gdn): fuse causal_conv1d and QKV split for GDN prefill
#382 opened Jun 8, 2026 by elwhyjay Contributor Loading…
6
fix(scheduler): publish prefix to radix tree during prefill for non-hybrid models
#381 opened Jun 8, 2026 by qywu Collaborator Loading…
12
fix(cache): Coarsely fence the compute stream behind the host loadback stream on. inactive
#370 opened Jun 6, 2026 by LorrinWWW Contributor Loading…
3
[Bugfix] fix smg command argument cannot be used multiple times inactive
#366 opened Jun 6, 2026 by lengrongfu Loading…
1
4
[Bugfix] fix miss help command inactive
#362 opened Jun 5, 2026 by lengrongfu Loading…
1
[Bugfix]fix cli logger not set level inactive
#360 opened Jun 5, 2026 by lengrongfu Loading…
3
feat(rl): weight-transfer control plane for RL online weight sync inactive
#342 opened Jun 2, 2026 by qywu Collaborator • Draft
1
feat(mla): support custom tree masks in decode inactive
#338 opened Jun 2, 2026 by mesaleh Loading…
1
fix(kernel): tile merge_state over heads to avoid >1024 block inactive
#330 opened Jun 1, 2026 by elwhyjay Contributor Loading…
1
feat (L3 KVStore): prefetch and backup support
#293 opened May 28, 2026 by ehuohz Loading…
@XucSh
15
perf(model_loader): multi-threaded safetensors weight loading inactive
#287 opened May 28, 2026 by yuanqingz Loading…
7
Add Triton sampling backends alongside FlashInfer
#280 opened May 27, 2026 by FlamingoPg Contributor Loading…
29
ProTip! Updated in the last three days: updated:>2026-06-20.