Skip to content

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

New pull request New
31 Open 258 Closed
31 Open 258 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

Fix workgroup barrier deadlock
#312 opened Apr 24, 2026 by frost-intel • Draft
2
Enhance the benchmark scripts
#309 opened Apr 24, 2026 by czhu15 Loading…
6
[MoE] mv sycl kernel tests out of fusedmoe test folder
#307 opened Apr 23, 2026 by Liangliang-Ma Collaborator Loading…
1
[WIP][XPU][MLA] Add paged_decode kernel and Python wrapper for MLA
#306 opened Apr 23, 2026 by baodii Collaborator • Draft
add qwen workload shape
#304 opened Apr 22, 2026 by xinyu-intel Collaborator Loading…
4 tasks
8
Add fp8 mqa logits kernels to support sparse MLA based models
#299 opened Apr 21, 2026 by YangQun1 Contributor Loading…
4 tasks
18
[WIP] Optimize GDN chunk_fwd_o_kernel performance
#297 opened Apr 21, 2026 by YangQun1 Contributor • Draft
4 tasks
Add moe dynamic quant kernels
#296 opened Apr 20, 2026 by tvoas Loading…
20
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
[test][DNM] upgrade torch 2.12
#288 opened Apr 20, 2026 by jikunshang Collaborator Loading…
4 tasks
5
update vllm kernel benchmark scripts
#284 opened Apr 17, 2026 by 1pikachu Contributor Loading…
4
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
30
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
[1/N][GGUF] add ggml_dequantize kernel
#244 opened Apr 1, 2026 by zhenwei-intel Contributor Loading…
4 tasks
7
add Claude.md
#243 opened Mar 31, 2026 by jikunshang Collaborator Loading…
4 tasks
6
support mrope kernel (dont merge, only for testing)
#238 opened Mar 30, 2026 by yihuaxu Contributor Loading…
4 tasks
support gamma_rms_norm and rms_norm_gated operators
#236 opened Mar 30, 2026 by yihuaxu Contributor Loading…
4 tasks
Optimize l2norm in GDN kernel for Qwen3.5
#222 opened Mar 25, 2026 by YangQun1 Contributor • Draft
8
[ATTN] mix batch perf tuning
#218 opened Mar 24, 2026 by YizhouZ Collaborator Loading…
5
support gemma_rms_norm and rms_norm_gated kernels
#214 opened Mar 23, 2026 by yihuaxu Contributor Loading…
18
ProTip! Type g i on any issue or pull request to go back to the issue listing page.