tweetindex
TH

vLLM ✓

@vllm_project · joined 30 Mar 2024

A high-throughput and memory-efficient inference and serving engine for LLMs. Join https://t.co/lxJ0SfX5pJ to discuss together with the community!

48 600Followers
36Following
1 275Posts total
211.5KViews on collected posts

โพสต์ล่าสุด

⚡ New RTX local-agent optimizations include a vLLM speedup on Blackwell. @NVIDIARTXSpark reports: 🛠️ 1.2x vLLM performance on RTX PRO 6000 Blackwell ⚡ Up to 1.4x on a two-system DGX Spark cluster Great to see the local serving path getting faster across RTX and DGX Spark. 15.4K views · 89 likes · 8 reposts · 6 replies Open on X →
🎉 Congrats to @AntLingAGI on open-sourcing Ling-3.0-flash-Fin and FinFIRST! Open models and expert-built benchmarks are a great step toward more accessible and verifiable financial AI. Looking forward to seeing these workflows run at scale with vLLM. 🚀 7.6K views · 39 likes · 3 reposts · 2 replies Open on X →
Love seeing @lightseekorg use TorchSpec + vLLM to train three different K3 draft models, with the recipes open sourced too. Exactly the kind of training-serving collaboration we love to see 🚀 6K views · 59 likes · 8 reposts · 2 replies Open on X →
Thank you to the @SemiAnalysis_ team for the shoutout and for the collaboration on AgentX 🙏 Benchmarks are only useful when they measure the workloads people actually run, and AgentX measures the real thing: multi-turn, long-context agent traffic. vLLM is the engine for 4.9K views · 32 likes · 8 reposts · 3 replies Open on X →
Shoutout to the cracked team at @vllm_project that implemented recent agentic workload optimizations. (1/5)🧵 https://t.co/BsXCtLBwvU 49.7K views · 186 likes · 27 reposts · 7 replies Open on X →
Releasing the @Kimi_Moonshot K3 Draft Collection — 3 draft models (EAGLE-3, DFlash2, DSpark) trained with TorchSpec and @vllm_project on @NVIDIAAI GB200. 🚀 We also shared the data recipes. More on the blog → https://t.co/5FdWfvYNm0 https://t.co/WjaJzEcBLp 43.7K views · 62 likes · 13 reposts · 2 replies Open on X →
K2-Horizon has day-0 support in vLLM, and IFM released intermediate checkpoints, detailed data-construction recipes, the training code, and fine-grained logs alongside the weights. 📷 512K context and Apache-2.0 from 3.7B up, with reasoning and tool calling in the checkpoints 10.2K views · 112 likes · 20 reposts · 5 replies Open on X →
🎉 Congrats to @deepseek_ai on DeepSeek-V4-Flash-Vision-Exp, the first multimodal model in the V4 family! vLLM serves it now. A vision encoder and aligner on the 285B/13B V4-Flash MoE backbone, with text-agent scores holding steady. 🚀 🔗 https://t.co/sxl7k5w9rs https://t.co/X162S 19.1K views · 254 likes · 27 reposts · 17 replies Open on X →
🎉 Congrats to @SparkLLM on releasing Spark-X2.5-4B and 1.7B! Compact on-device agent models: 200+ languages, native 1M context. Both have day-0 vLLM support via Spark's out-of-tree general plugin. 33.6K views · 318 likes · 16 reposts · 10 replies Open on X →
We worked alongside @inferact and @FireworksAI_HQ on the investigation. 🔍 We share that bar for consistency. Credit to @FireworksAI_HQ for taking the extra time to verify, and to @Zai_org for the quick API update. 🎉 15.3K views · 136 likes · 19 reposts · 15 replies Open on X →
On Tuesday, capping off a full day of speakers at the first vLLM Conference, the vLLM community gathered for a rooftop happy hour at sunset. The event hit capacity, and sunset over the city was a great backdrop. Thank you to @AMD and @inferact for co-hosting! More meetups to htt 6.1K views · 65 likes · 7 reposts · 9 replies Open on X →

เทียบกับบัญชีขนาดเดียวกัน

11 โพสต์จาก 90 วันที่ผ่านมา เทียบกับช่วง 10K–100K ผู้ติดตาม แสดงในวงกว้าง แต่มีผู้ชมตอบสนองน้อย.

ยอดดูมัธยฐาน15 252บัญชีนี้924ค่ามัธยฐานของ 10K–100K
การเข้าถึง, %31.38%บัญชีนี้3.62%ค่ามัธยฐานของ 10K–100K
การมีส่วนร่วม, %1.03%บัญชีนี้1.52%ค่ามัธยฐานของ 10K–100K
ตัวชี้วัดบัญชีนี้ค่ามัธยฐานของ 10K–100Kอัตราส่วน
ยอดดูมัธยฐานต่อโพสต์15 25292416.5×
การเข้าถึง (ยอดดู ÷ ผู้ติดตาม)31.38%3.62%8.67×
อัตราการมีส่วนร่วม1.03%1.52%0.68×

บัญชีอื่นในช่วงนี้ →   เปรียบเทียบกับบัญชีอื่น →   ค่าอ้างอิงเหล่านี้คำนวณอย่างไร →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

6.1K29 Aug
15.3K30 Aug
33.6K1 Sep
19.1K
10.2K3 Sep
43.7K
49.7K
4.9K
6K4 Sep
7.6K
15.4K

Last 11 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.34%29 Aug
1.12%30 Aug
1.03%1 Sep
1.56%
1.38%3 Sep
0.19%
0.45%
0.88%
1.14%4 Sep
0.61%
0.69%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes69.3%1 352 in total
Reposts8.0%156 in total
Replies4.0%78 in total
Quotes1.2%23 in total
Bookmarks17.5%341 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

บัญชีที่คล้ายกัน

Frequently asked questions about @vllm_project

How many followers does @vllm_project have?

48 600 followers.

How many posts has @vllm_project published?

1 275 posts.

How do posts by @vllm_project perform?

Collected posts: 11. Views: 211 475. Likes: 1 352.