Skip to content

Pull requests: vllm-project/vllm-xpu-kernels

New pull request New
35 Open 298 Closed
35 Open 298 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

[Benchmark] Adjust FA benchmark configs for B60 memory constraints
#359 opened May 20, 2026 by 1pikachu Contributor Loading…
2
fa2 xe2: precompile shared header umbrella for attn_kernels_xe_2
#350 opened May 13, 2026 by jasonboukheir Contributor • Draft
1
fa2 xe2: hoist Q/KV dtype dispatch out of policy_dispatch_impl
#349 opened May 13, 2026 by jasonboukheir Contributor • Draft
cmake: emit -cl-intel-256-GRF-per-thread regardless of AOT
#348 opened May 13, 2026 by jasonboukheir Contributor • Draft
cmake: expose kernel-build memory knobs via cache vars
#347 opened May 13, 2026 by jasonboukheir Contributor • Draft
cmake: include project root for quoted csrc/* includes
#346 opened May 13, 2026 by jasonboukheir Contributor • Draft
cmake: add VLLM_XPU_LIBS_ONLY + prebuilt-kernel-lib hooks
#345 opened May 13, 2026 by jasonboukheir Contributor • Draft
benchmark: extend to support trition attention kernel
#343 opened May 13, 2026 by xinyu-intel Collaborator Loading…
4 tasks
11
[GDN] Spec-decoding-aware attention kernel
#336 opened May 12, 2026 by jasonboukheir Contributor Loading…
add relu2 kernel
#329 opened May 7, 2026 by chaojun-zhang Contributor Loading…
4 tasks
6
add the roofline analysis metrics for gemm, attention and MoE benchmarks
#325 opened May 6, 2026 by czhu15 Contributor Loading…
9
[WIP]refactor template gen
#324 opened May 6, 2026 by jikunshang Collaborator Loading…
4 tasks
19
[DNM] upgrade oneapi 2026.0
#321 opened May 3, 2026 by jikunshang Collaborator Loading…
4 tasks
11
optimize VLLM rms_norm kernel perf.
#316 opened Apr 29, 2026 by nc-BobLee Loading…
1 of 4 tasks
13
[MoE] mv sycl kernel tests out of fusedmoe test folder
#307 opened Apr 23, 2026 by Liangliang-Ma Collaborator Loading…
5
[WIP] Optimize GDN chunk_fwd_o_kernel performance
#297 opened Apr 21, 2026 by YangQun1 Contributor • Draft
4 tasks
Sycltla BF16 GEMM
#294 opened Apr 20, 2026 by xinyu-intel Collaborator • Draft
4 tasks
[Cache] support HND in reshape_and_cache_flash
#292 opened Apr 20, 2026 by zufangzhu Collaborator Loading…
Replace int with size_t for size/count/stride/index variables across csrc
#291 opened Apr 20, 2026 by jikunshang Collaborator Loading…
8
upgrade torch 2.12
#288 opened Apr 20, 2026 by jikunshang Collaborator Loading…
4 tasks
6
Add chunk_causal_conv1d_opt_kernel in GDN for Qwen3.5
#278 opened Apr 15, 2026 by YangQun1 Contributor • Draft
4 tasks
split attention template via data types
#270 opened Apr 13, 2026 by xinyu-intel Collaborator Loading…
4 tasks
6
optimized fused_grouped_topk SYCL kernel for MoE expert routing
#253 opened Apr 7, 2026 by xiaolong-intel Loading…
4 tasks
32
Enalbe fused softmax/sigmoid + topk path for 1024 experts
#252 opened Apr 3, 2026 by JianyuLi01 Loading…
4 tasks
5
get memory info
#249 opened Apr 2, 2026 by mayuyuace Collaborator • Draft
15
ProTip! Exclude everything labeled bug with -label:bug.