Junrong Lin @OcssLin
MTS @Alibaba_Qwen on MLsys, building SGLang @lmsysorg | Prev. @DukeU junronglin.com California Joined April 2022-
Tweets99
-
Followers102
-
Following312
-
Likes347
🧠For Qwen3-Next’s Day 0 support in SGLang, one tricky part was enabling spec decoding with the Hybrid Linear Model—since SSM & conv caches only store the last position (unlike KV cache). 🚀After tons of effort with @qingquan_song, we achieved >2× speedup! Benchmarks below
🧠For Qwen3-Next’s Day 0 support in SGLang, one tricky part was enabling spec decoding with the Hybrid Linear Model—since SSM & conv caches only store the last position (unlike KV cache). 🚀After tons of effort with @qingquan_song, we achieved >2× speedup! Benchmarks below https://t.co/M4mSNbUDgI
Special thanks to my old friends from the SGLang community especially @hebiao064 @qingquan_song and more (sry I don’t know their X account 🥹) who help support the hybrid model MTP. For linear attention, the eviction during eagle verification phase is different from the regular…
Special thanks to my old friends from the SGLang community especially @hebiao064 @qingquan_song and more (sry I don’t know their X account 🥹) who help support the hybrid model MTP. For linear attention, the eviction during eagle verification phase is different from the regular…
🚀 Introducing Qwen3-Next-80B-A3B — the FUTURE of efficient LLMs is here! 🔹 80B params, but only 3B activated per token → 10x cheaper training, 10x faster inference than Qwen3-32B.(esp. @ 32K+ context!) 🔹Hybrid Architecture: Gated DeltaNet + Gated Attention → best of speed &…
We’re live! 🎉 This is the official account for slime — an open-source, SGLang-native post-training framework for RL scaling. Kicking things off with our first milestone → v0.1.0 release 🧪 Blog: thudm.github.io/slime/blogs/re… Follow us to run RL faster ⚡️
cool
😎Grad to see my first participated project at Qwen is finally out. More awesome work is coming
😎Grad to see my first participated project at Qwen is finally out. More awesome work is coming
We are using SGLang at really large scale RL, and it’s been working great :)
We are using SGLang at really large scale RL, and it’s been working great :)
More on QAT: 1. QAT explanation: pytorch.org/blog/quantizat… 2. MXFP4 QAT is supported in NVIDIA ModelOpt: github.com/NVIDIA/TensorR… 3. A quick drawing of how gpt-oss is trained in my understanding:
🚀 Introducing the first OSS example of fine-tuning gpt-oss with MXFP4 QAT! Powered by NVIDIA ModelOpt + SGLang. Highlights 1. Fine-tune gpt-oss while keeping the original MXFP4 format 2. Preserve FP4 efficiency and recover accuracy 3. Deploy seamlessly with SGLang! Full Blog👇
chad
✅ We’re excited to support @Alibaba_Qwen’s Qwen3-Coder on SGLang! With tool call parser and expert parallelism enabled, it runs smoothly with flexible configurations. Just give it a try! 🔗 github.com/zhaochenyang20…
✅ We’re excited to support @Alibaba_Qwen’s Qwen3-Coder on SGLang! With tool call parser and expert parallelism enabled, it runs smoothly with flexible configurations. Just give it a try! 🔗 github.com/zhaochenyang20…
Bye Qwen3-235B-A22B, hello Qwen3-235B-A22B-2507! After talking with the community and thinking it through, we decided to stop using hybrid thinking mode. Instead, we’ll train Instruct and Thinking models separately so we can get the best quality possible. Today, we’re releasing…
Grok4 🚀 x.com/i/events/19427…
salute
Meet Qwen-VLo, your AI creative engine: • Concept-to-Polish: Turn rough sketches or text prompts into high-res visuals • On-the-Fly Edits: Refine product shots, adjust layouts or styles with simple commands • Global-Ready: Generate image in multiple languages • Progressive…
We're excited to release OME, which is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs). It optimizes the deployment and operation of LLMs by automating model management, intelligent runtime selection, efficient resource…
Huge thanks to @AMD for donating an MI350 to SGLang! This advanced AI accelerator is making a meaningful difference—enabling us to move faster in developing scalable LLM systems and pushing the limits of inference optimization. Special thank to our awesome infra partner…
🚀 Proud to introduce the Qwen3-Embedding and Qwen3-Reranker Series – setting new standards in multilingual text embedding and relevance ranking! ✨ Highlights: ✅ Available in 0.6B / 4B / 8B versions ✅ Supports 119 languages ✅ State-of-the-Art performance on MMTEB , MTEB ,…
san shi @sanshi12333
1 Followers 39 Following
66RING @66ringnotcute
12 Followers 200 Following Chaotic random access. Chaotic Futurism. May chaos take the world. INFJ-T. 66RING@github
Lisa @seller_lisa41
178 Followers 3K Following
Aviral @aviral1531
47 Followers 1K Following
Mert Ünsal @mertunsal2020
1K Followers 793 Following Agent Lead @browser_use, prev. RL Research at @ProjectNumina @ETH_en
Taishi Nakamura @Setuna7777_2
2K Followers 6K Following Working on scalable and efficient LLM (MoE pretraining, RL, reasoning). CS MS at @sciencetokyo_en Intern @SakanaAILabs
Violetta @Imeannorh9141
38 Followers 2K Following You are never too old to set another goal or to dream a new dream.
MeganWollaston @6Zc3B08f2yl16
13 Followers 477 Following
Simon @AI_Homelab
257 Followers 537 Following Teacher, PICTS School Admin, Student in MAS Didactics of media and computer science (UZH, PHSZ, HSLU), Techno Optimist, tinkerer, ML enthusiast
Wenting Zhao @wzhao_nlp
5K Followers 609 Following reasoning & llms @Alibaba_Qwen Opinions are my own
Yun Dai @yundaiiiii
92 Followers 152 Following @openai | prev: @windsurf @LinkedIn https://t.co/zYQ2JvaRc5
Brayden Zhong @braydenzhong
4 Followers 55 Following
Seiji Eicher @seiji_________
99 Followers 429 Following Ray + vLLM = 💘 @ Anyscale | Prev: @Apple, @Stanford
Irvolar @Irvolar25260
91 Followers 2K Following
LMSYS Org @lmsysorg
8K Followers 180 Following Large Model Systems Organization: Join our Slack: https://t.co/mSPNyKTLTS We developed SGLang https://t.co/jEqIJcGwGA, Chatbot Arena (now @lmarena_ai), and Vicuna!
Chand @Chand7449215950
56 Followers 3K Following
Vartan Polodyan @VarPol
194 Followers 6K Following
cher @chenhao76566284
45 Followers 943 Following
habaohabahabo @71639820lz
80 Followers 3K Following
旭美雪 @xmixu440185
1 Followers 269 Following
Casper Hansen @casper_hansen_
10K Followers 461 Following NLP Scientist | AutoAWQ Creator | Open-Source Contributor
Zhipeng(Jason Z) Wang... @PKUWZP
640 Followers 974 Following LLM Systems/Infra/Multimodal/RL, PhD @RiceUniversity, Sr Manager @LinkedIn. ex:{@GoogleResearch, @AWS, @Apple, @PKU1898 @WashU}, TSC Committer @DeepSpeedAI
Harsha Bandi @harshadev12
138 Followers 4K Following AI Explorer | Web Developer | Software Engineer
JingyuanLiu @JingyuanLiu123
3K Followers 429 Following https://t.co/D7zLeTZRMh is all you need | Opinions are my own
dazhi jiang @Zzhi_Jiang
3 Followers 320 Following
Qubitum @qubitium
1K Followers 4K Following I make models go brrr..... @ModelCloudAI founder Committer to SGLang, vLLM, GPTQModel. AI sw + hw { Go, Python, Kotlin } Quantization Accelerator
Ying Sheng @ying11231
12K Followers 731 Following @lmsysorg @sgl_project | Prev. @xAI @Stanford | Assist Prof @UCLA. (delayed) | Do it anyway | Live to fight another day
eulers mask @OMEDGE
99 Followers 3K Following
Jun (Richard) Wang @AI_richard
36 Followers 1K Following
Jin Pan @JinPan547630
4 Followers 49 Following SJTU | UMich | UWisc-Madison | AMD | Mastering out and looking for full-time
zhyncs @zhyncs42
3K Followers 538 Following 🌁 OPINIONS ARE MY OWN, Homepage https://t.co/saCowtppUm, Just for fun @lmsysorg SGLang, Prev @basetenco @meituan @Baidu_Inc
Yi Zhang @zy392362
13 Followers 29 Following
Grad @Grad62304977
7K Followers 2K Following
Chris 🇺🇸 @ischriswang
101 Followers 709 Following A 10x worker. Adapt what is useful, reject what is useless, and add what is specifically your own. - Bruce Lee.
RoseAlick @kFhn45LZ99F6Rj
11 Followers 1K Following
MMM @MMM1897775
9 Followers 3K Following
Deveaw @Deveaw16867
18 Followers 826 Following
Ce Gao @gaocegege
7K Followers 788 Following Co-founder and CEO @TensorChord, building postgres-based vector extension https://t.co/7WGvl1sR56 | Father of 1 cat | Married
Zhiqing Sun @EdwardSun0909
19K Followers 1K Following Agents @Meta MSL TBD Lab. previously posttraining research @OpenAI train LLMs to do things: deep research, chatgpt agent, etc. CS PhD @LTIatCMU
Mert Ünsal @mertunsal2020
1K Followers 793 Following Agent Lead @browser_use, prev. RL Research at @ProjectNumina @ETH_en
Simon @AI_Homelab
257 Followers 537 Following Teacher, PICTS School Admin, Student in MAS Didactics of media and computer science (UZH, PHSZ, HSLU), Techno Optimist, tinkerer, ML enthusiast
Seiji Eicher @seiji_________
99 Followers 429 Following Ray + vLLM = 💘 @ Anyscale | Prev: @Apple, @Stanford
Zhipeng(Jason Z) Wang... @PKUWZP
640 Followers 974 Following LLM Systems/Infra/Multimodal/RL, PhD @RiceUniversity, Sr Manager @LinkedIn. ex:{@GoogleResearch, @AWS, @Apple, @PKU1898 @WashU}, TSC Committer @DeepSpeedAI
Yun Dai @yundaiiiii
92 Followers 152 Following @openai | prev: @windsurf @LinkedIn https://t.co/zYQ2JvaRc5
Byron Hsu @hsu_byron
4K Followers 2K Following ML system @xAI | @lmsysorg @liger_kernel @flyteorg @theASF
Yi Zhang @zy392362
13 Followers 29 Following
prinsyin @prinsyin1
2 Followers 5 Following
Thomas Ip @_thomasip
264 Followers 205 Following Chat with your dream waifu 👉 https://t.co/kC0nx1eO49 AI @scale_ai | Crypto HFT co-founder
Horace He @cHHillee
42K Followers 537 Following @thinkymachines Formerly @PyTorch "My learning style is Horace twitter threads" - @typedfemale
Woosuk Kwon @woosuk_k
6K Followers 628 Following @thinkymachines | @vllm_project | PhD-ing @Berkeley_EECS
Wenting Zhao @wzhao_nlp
5K Followers 609 Following reasoning & llms @Alibaba_Qwen Opinions are my own
Ce Gao @gaocegege
7K Followers 788 Following Co-founder and CEO @TensorChord, building postgres-based vector extension https://t.co/7WGvl1sR56 | Father of 1 cat | Married
Ligeng Zhu @LigengZhu
2K Followers 2K Following Research Scientist at @Nvidia exploring efficient training , previously @MIT, @SFU and @ZJU_China.
Yi Wu @jxwuyi
1K Followers 103 Following AI/RL researcher, Assistant Prof. at @Tsinghua_Uni, leading the RL lab at @AntResearch_, PhD at @berkeley_ai, frequent flyer and milk tea lover.
Ryan Hanrui Wang @hanrui_w
2K Followers 748 Following Building @Eigen_AI_Labs | AEI = Artificial Efficient Intelligence | PhD @MIT | Ex-@NVIDIA @XilinxInc | Efficient AI, Computer Architecture.
Haibin (on leave) @eric_haibin_lin
2K Followers 977 Following On the path to AGIs. Bytedance Seed LLM Systems, @verl_project, Megascale. Prev. @AmazonScience @ApacheMXNet
JingyuanLiu @JingyuanLiu123
3K Followers 429 Following https://t.co/D7zLeTZRMh is all you need | Opinions are my own
zhuzilin @zhuzilinallen
41 Followers 397 Following https://t.co/wRjPFkVT1r | https://t.co/qg295LHlLz
slime @slime_framework
210 Followers 3 Following The LLM post-training framework for RL Scaling. https://t.co/4ILpx8hfKN
Edward Z. Yang @ezyang
14K Followers 1K Following I work on PyTorch at Meta. Chatty alt at @difficultyang.
Chen Cheng @cherry_cc12
1K Followers 114 Following maintainer of modelscope community, contributor of Qwen
Nano Banana @NanoBanana
44K Followers 1 Following Nano Banana 🍌 the world's most powerful image editing and generation model! Try it for free in the @GeminiApp
Tongyi Lab @Ali_TongyiLab
9K Followers 20 Following We advance the development of AGI and foster open source collaboration towards a smarter future.
Tianbao Xie @TianbaoX
3K Followers 2K Following Ph.D. candidate @XLangNLP lab and @hkunlp2020 . Incoming @OpenAI . Advised by @taoyds and @ikekong . 🤝 @Alibaba_Qwen @SFResearch
Graham Neubig @gneubig
40K Followers 710 Following Associate professor @LTIatCMU. Co-founder/chief scientist @allhands_ai. I mostly work on modeling language.
Aleksa Gordić (水�... @gordic_aleksa
26K Followers 229 Following getting us to singularity with friends computers can be understood: https://t.co/doHE1Qv2Sj x @GoogleDeepMind @Microsoft tensor core maximalist
Shenggui Li (Frank) @frankkklee
114 Followers 213 Following 📖 PhD student @NTUsg 🚀 Building SpecForge, SGLang, slime 💾 Prev@ColossalAI, Open-Sora, Sequence Parallelism, founding member @HPCAITech
Zephyr @zephyr_z9
32K Followers 508 Following Tech, AI, Semiconductors, Stocks, Finance. DMs are open
Jiantao Jiao @JiantaoJ
2K Followers 124 Following Director of Research & Distinguished Scientist at @NVIDIA, Professor at UC Berkeley EECS and Statistics. Building AGI/ASI
Adina Yakup @AdinaYakup
11K Followers 839 Following @huggingface 🤗 | AI Research 🔍 Chinese ML community. opinions are my own.
硅谷王川 Chuan @Svwang1
165K Followers 473 Following Twitter is my Chain-Of-Thought. Reading history is my end-to-end training. Not financial advice. 一言不合就拉黑。评论区只对订阅用户开放。 Runner: 1 km, 3'49; 5 km, 23'07
SangBin Cho @Saaaang94
3K Followers 488 Following reasoning @xAI | prev-founding engineer @anyscalecompute | senior committer of @raydistributed | committer @vllm_project Sglang | Github: rkooo567
Sewon Min @sewon__min
14K Followers 819 Following Assistant professor @Berkeley_EECS @berkeley_ai || Research scientist at @allen_ai || PhD from @uwcse @uwnlp
Qian Huang @qhwang3
14K Followers 330 Following prev @xai | CS PhD student @StanfordAILab (on leave)
Qwen AI Fans @QwenAIFans
2K Followers 102 Following @lihailallc We share Qwen AI powered innovations to enrich people's life.
Yinya Huang @YinyaHuang
189 Followers 634 Following Postdoc @ETH_AI_Center, @ETH. Prev @CityUHongKong, @TencentGlobal. #LLM, #NLProc & #AI
Eigen AI @Eigen_AI_Labs
397 Followers 23 Following Built by researchers and engineers from MIT, we are pursuing Artificial Efficient Intelligence (AEI). Try GPT-OSS support: https://t.co/BQfsnXIGFo.
Fan Zhou @FaZhou_998
1K Followers 835 Following Qwen Coding @Alibaba_Qwen. Prev: Core member @XLangNLP, Intern @MSFTResearch.
NovaSky @NovaSkyAI
3K Followers 15 Following Next-generation Open Vision and AI @BerkeleySky Contact: [email protected]
Shiyi Cao @shiyi_c98
1K Followers 606 Following Student Lead @NovaSkyAI, PhD student @UCBerkeley @BerkeleySky, MSc @ETH, B.S @sjtu1896, llm and system
青龍聖者 @bdsqlsz
10K Followers 729 Following CPP:@pika_labs @SkyReels BusinessCooperation [email protected] [email protected] Architectural Model↓ [email protected] https://t.co/aGSCaF4wt4Trends for United States
You might like
