vllm-xpu-kernels
vllm-xpu-kernels is 目的与范围 为 downstream/v0.31.0 的 Qwen3.8-Flash-Next TP4 INT4、TP8 INT4/FP8 以及 Qwen4-27B dense TP2 FP8、TP1/TP2 INT4 提供 SYCL/SYCL-TLA kernel。重点覆盖 M=1–8、MTP draft=4/B1 和大 prefill，减少空算、内存往返及主机提交开销。 配套模型、met.... It is ranked #223 on the Dev Radar, in AI dev tools, first seen 6 days ago and shared in 5 posts (49.7k views).
Enable Qwen3.8-flash-next 8 cards fp8 & int4 and optimize qwen4-27b by hzjane · Pull Request #22 · analytics-zoo/vllm-xpu-kernels · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation Enable Qwen3.8-flash-next 8 cards fp8 & int4 and optimize qwen4-27b - # 22 # 22 Merged hzjane merged 10 commits into…
What people said about vllm-xpu-kernels on X
Qwen4-27B spotted in Intel intel-xpu-kernels repo ! Work for Qwen4-27B support is already underway, this only means one thing and you know what that is. LFGG @Alibaba_Qwen Give us Qwen4-27B soon ! https://github.com/analytics-zoo/vllm-xpu-kernels/pull/22/changes
— @ItsmeAjayKV, 6 days ago · 267 likes · see the post
In anticipation of Qwen4-27B !! This is what Qwen3.8-27B Unsloth UD-Q4_K_M is currently capable of ! Running locally on my RTX 3090 (unlocked 3090) via llama.cpp Here is a one-shot, no harness, no tools, single turn result of a three.js scene of a floating island with a pagoda, a castle, a waterfall falling into…
— @ItsmeAjayKV, 5 days ago · 143 likes · see the post
Qwen 4 showing up Enable Qwen3.8-flash-next 8 cards fp8 & int4 and optimize qwen4-27b https://github.com/analytics-zoo/vllm-xpu-kernels/pull/22
— @TechMDAI, 6 days ago · 22 likes · see the post
Alternatives to vllm-xpu-kernels
- goo.gle — Officially in beta, the AppFunctions API is opening up powerful new ways to integrate your functionality.
- Kimi AI with K3.1 Pro — Try Kimi K3.1 Pro to tackle complex coding projects, build 3D models, conduct financial research, and take on more…
- Agents in flight — Give it a try
- Baseten — This session is our most in-demand yet. See you there
- project-maya — Checkout Maya
- deepinfer — You gotta love Deepseek. This is awesome stuff!
vllm-xpu-kernels in numbers
- Rank on the Dev Radar: #223 of 8798
- Shared in 5 posts by 4 accounts: @ItsmeAjayKV, @TechMDAI, @Mayhem4Markets, @itsjustmarky
- 49.7k views on those posts
- First seen 6 days ago, last shared 5 days ago
- Pricing seen by AGK Intelligence: open source
- Market: AI dev tools
FAQ
What is vllm-xpu-kernels?
目的与范围 为 downstream/v0.31.0 的 Qwen3.8-Flash-Next TP4 INT4、TP8 INT4/FP8 以及 Qwen4-27B dense TP2 FP8、TP1/TP2 INT4 提供 SYCL/SYCL-TLA kernel。重点覆盖 M=1–8、MTP draft=4/B1 和大 prefill，减少空算、内存往返及主机提交开销。 配套模型、met... It was first shared on X 6 days ago and is ranked #223 on the Dev Radar.
Is vllm-xpu-kernels free?
It is open source.
Who shared vllm-xpu-kernels?
4 accounts on X, including @ItsmeAjayKV, @TechMDAI, @Mayhem4Markets, in 5 posts totalling 49.7k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:27 UTC. Full method.