Skip to content

Pull requests: lightseekorg/tokenspeed

New pull request New
24 Open 491 Closed
24 Open 491 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

chore(kernel): bump flashinfer to 0.6.13, add <cfloat> include
#539 opened Jun 27, 2026 by jaywme Collaborator • Draft
1
Fix gathered MXFP4 activation scales in Gluon MoE
#534 opened Jun 26, 2026 by qedawkins Contributor Loading…
9
test: glm-5.2 agentic bench
#532 opened Jun 26, 2026 by syuoni Member • Draft
[WIP] Initial glm 5.2 support on amd
#528 opened Jun 26, 2026 by borontion Contributor • Draft
feat: support qwen3.5 on Hopper GPUs
#520 opened Jun 25, 2026 by XuZhang99 • Draft
[WIP] feat:support qwen3.5 dflash
#510 opened Jun 24, 2026 by minedec Contributor • Draft
3
fix(runtime): harden MTP decode path against NaN, overflow, and state…
#506 opened Jun 24, 2026 by tuanzhangCS Contributor Loading…
6
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
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 inactive
#412 opened Jun 10, 2026 by netanel-haber Loading…
4
[WIP] feat(config): runtime config decoupling(design for reference) inactive
#383 opened Jun 8, 2026 by rjzhb Collaborator • Draft
1
perf(gdn): fuse causal_conv1d and QKV split for GDN prefill
#382 opened Jun 8, 2026 by elwhyjay Contributor Loading…
8
fix(scheduler): publish prefix to radix tree during prefill for non-hybrid models inactive
#381 opened Jun 8, 2026 by qywu Collaborator Loading…
13
fix(cache): Coarsely fence the compute stream behind the host loadback stream on.
#370 opened Jun 6, 2026 by LorrinWWW Contributor Loading…
4
feat (L3 KVStore): prefetch and backup support inactive
#293 opened May 28, 2026 by ehuohz Loading…
@XucSh
16
Add Triton sampling backends alongside FlashInfer inactive
#280 opened May 27, 2026 by FlamingoPg Contributor Loading…
30
perf(deepseek-v4): vectorize read_deepseek_v4_indexer_fp8_cache
#238 opened May 24, 2026 by yuanqingz Loading…
11
feat(trtllm-MHA): support mixed prefill/decode batches
#176 opened May 18, 2026 by rjzhb Collaborator • Draft
4 tasks done
@LorrinWWW
11
perf(cache): overlap target and draft KV loadback independently
#6 opened May 6, 2026 by LorrinWWW Contributor Loading…
@LorrinWWW
3
ProTip! Follow long discussions with comments:>50.