Skip to content

Pull requests: sgl-project/sgl-kernel-npu

New pull request New
44 Open 345 Closed
44 Open 345 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

[deepep] fix notify use ub exceeds the limit
#421 opened Apr 2, 2026 by zuje123 Loading…
1
[WIP]add Prefill causal conv1d
#418 opened Apr 1, 2026 by AndyKong2020 Loading…
1
Init SGLang Ascend Agent structure
#417 opened Mar 31, 2026 by shengzhaotian Loading…
5
add partial_rope_qk_inplace
#416 opened Mar 31, 2026 by xiaobaicxy Loading…
5
Use Physical Core for scale_shift_kernel
#415 opened Mar 31, 2026 by gjsheu Loading…
1
Mlp triton matmul replace
#414 opened Mar 31, 2026 by JiaruiChang5268 Loading…
1
add dispatch_ffn_combine_bf16 kernel for deepep
#410 opened Mar 27, 2026 by zuje123 Loading…
1
[WIP] add fuse_deep_moe_no_buffer for enable-torch-compile
#409 opened Mar 27, 2026 by jiaming1130 Loading…
1
for qwen3-next:add kernel fused split qkvgate gemma rmsnorm rope
#405 opened Mar 23, 2026 by McZyWu Loading…
6
add fused_deep_moe test for dispatch_ffn_combine
#400 opened Mar 18, 2026 by zuje123 Loading…
6
adpat mutilServer
#386 opened Feb 28, 2026 by zzx-study Loading…
1
LoRA: Implementing kernels using CUBE computation unit
#384 opened Feb 27, 2026 by vlserov Loading…
19
[WIP] Deepep A5 normal and low-latency operators
#381 opened Feb 24, 2026 by oagniqgnat Loading…
19
【WIP】add Pipeline mode
#380 opened Feb 24, 2026 by zzx-study Loading…
9
MMLU benchmark for different inverse implementations
#374 opened Feb 11, 2026 by gioelegott Loading…
10
Add scripts for building CMake files
#372 opened Feb 11, 2026 by 1329009851 Loading…
20
(tri_inv) (pto-isa) implement AIV triangular inverse using pto-isa
#369 opened Feb 6, 2026 by zouzias Loading…
8
wrap triton_kernels into callable that can be traced into a graph
#368 opened Feb 5, 2026 by lawtherWu Loading…
4
Add AscendC triangular inverse using AIC and AIV
#366 opened Feb 4, 2026 by gioelegott Loading…
13
[Doc] Delete DeepWiki in README.md
#347 opened Jan 26, 2026 by Agent-Skill-007 Loading…
1
[feat]add apply_top_k_top_p_min_p op
#340 opened Jan 22, 2026 by wangxinwei21 Loading…
3
deeepep normal support shmem with asymmetric tensor
#328 opened Jan 19, 2026 by zuje123 Loading…
7
Dynamo do not support 'with torch.npu.device', delete it
#319 opened Jan 15, 2026 by DevinP16 Loading…
3
Test reduce
#307 opened Jan 7, 2026 by littleyellowbicycle Loading…
22
[bug fix] Dispatch FP8
#296 opened Jan 4, 2026 by kaniel-outis Loading…
12
ProTip! Mix and match filters to narrow down what you’re looking for.