不少团队上线大模型服务,背后跑的都是 vLLM 这个开源引擎。有人写了篇长文,把它从里到外拆开讲:请求怎么排队调度、显存怎么省着用、多张显卡怎么分工,配图不少,写得也扎实。想弄明白自家模型服务为什么快、为什么慢,读它正好。https://www.aleksagordic.com/blog/vllm

Channel
开发者日报
@cndevdaily
On this record: Growth · Engagement · Reactions · Posts · Citations · Cite this entry
1,932subscribers
+8 since we began measuring on 6 August 2026
Risers and fallers across the register · movement among entries of 1,000–3,162.
Register entry
| Telegram ID | -1001365329238 |
|---|---|
| Type | Channel |
| Username | @cndevdaily |
| Created | 31 December 2017 — measured — cross-checked against a third-party dataset (TGDataset) |
| First recorded | 6 August 2026 |
| Last confirmed live | 13 August 2026 |
| Measurements held | 4 |
| Confirmed unchanged | 1 time, most recently 13 August 2026 |
| On Telegram | t.me/cndevdaily |
Growth
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 13 Aug 2026, 08:35 | 1,932 | +1 |
| 10 Aug 2026, 15:42 | 1,931 | +7 |
| 7 Aug 2026, 06:41 | 1,924 | no change |
| 6 Aug 2026, 13:31 | 1,924 | first reading |
Engagement
21 posts held, back to 18 July 2026 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 2 pagesof Telegram’s post history, 20 posts per page.
- ERR · 30 days
- 15.0%
- avg views ÷ 1,932 subscribers
- Avg views / post
- 290
- 21 posts measured
- Reaction rate
- 0.127%
- reactions ÷ views · ER floor
- Posts in window
- 21
- of 21 held
ERR is average views per post over the last 30 days divided by subscribers, the definition TGStat uses, so this figure is comparable with the one you will see elsewhere. It falls structurally as a channel grows: a high ERR on a small channel and a low one on a large channel describe reach mathematics, not quality. We publish the figure and the sample it came from and pass no verdict on it.
ER is defined industry-wide as (forwards + reactions + comments) ÷ views— note the denominator is views, not subscribers. Telegram’s public web preview carries views and reactions but not forward or comment counts, so the reaction rate above is the reactions term only and is therefore a floor: the true ER for this channel is higher by an amount we have not measured and will not estimate. It is computed over the 3 of 21 measured posts that carry a reaction reading, and over those same posts' views.
| Window | Rolling 30 days · latest post in window 7 August 2026 |
|---|---|
| Posts held | 21 (18 July 2026 – 7 August 2026) |
| Views total | 6,082 |
| Reactions total | 1 |
| Forwards / comments | not exposed by the public surface — not measured, not estimated |
| Readings taken | 7 Aug 2026, 17:14 UTC |
Views are a single reading per post, taken at the time above. A post published in the last day or two is still accumulating views, which pulls the 30-day average down slightly. That is a property of the standard definition rather than a fault in it, so we keep the definition rather than “correcting” the number into something nobody can reproduce.
Precision. Telegram publishes view counts on its public widget in short form — 8.12K, 3.7M — so any reading at or above 1,000 reaches us rounded to three significant figures, and only counts below 1,000 are exact. Averages and rates derived from them are shown to the same precision rather than to the unit: a figure like 3,701,250 would assert digits nobody measured.
Reaction counts are published per emoji and rounded the same way, so a total below 1,000 is exact and a larger one is a sum that may carry a rounded component from each emoji above 1,000. Because it is a sum, it does not look rounded — read a large reaction total as three significant figures per contributing emoji rather than as the figure it prints.
Reaction mix
1 reaction across 1 post, in 1 kind.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| ❤ | 1 | 100.0% |
No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.
Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.
Coverage. Reactions were read on 3 of the 21 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 1reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 21 most recent posts we hold, published 18 July 2026 to 7 August 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
Recent posts
AI 让生成漂亮代码变得零成本,开源项目的审查员快被淹没了。Rust 团队最近公开了一份规矩:仓库压着 1200 多个待审提交,原样搬运 AI 代码的会直接关掉。规矩写得很细,做开源维护的能直接参考,其他社区估计迟早也得跟上。https://blog.rust-lang.org/inside-rust/2026/08/05/rust-langrust-is-adopting-an-llm-policy/
凡是让用户发内容的产品,都得有人把关内容安不安全。Mistral 开源了一个专干这活的小模型,思路挺巧:审核规则不用写死,你用大白话问它就行,比如"这张图能给未成年人看吗",它就给出安全分数。一张 16G 显卡能跑,效果还压过比它大七倍的模型。https://mistral.ai/news/shieldstral/
漏洞编号现在也能批量造假了。一批 SQLite 高危漏洞报告被权威漏洞库打上严重评分,安全研究员去核证,发现全是 AI 编的:点名的函数在对应版本里根本不存在,攻击演示也跑不出任何崩溃。看完有点后怕,AI 写的安全报告,先验证再信。https://research.jfrog.com/post/sqlite-critical-cves-or-llm-slops/
有人分享他挑 AI 模型的新标准:先看速度,再看聪明程度。他的体会是,如今模型都够聪明了,输出慢于每秒 50 个词就让人等得心烦,文末还挂了个每秒上万个词的演示,快到你根本读不过来。我自己做软件也是这个感觉,快,本身就是一种好用。https://martinalderson.com/posts/speed-vs-intelligence/
把 CI/CD 管道当作生产系统来对待,不只是优先级调整,更是工程效能的底线思维。管道一堵,团队空转,所谓敏捷就成了一句口号。可靠交付从尊重构建系统开始。https://sundry.jerryorr.com/2026/07/31/development-pipeline-is-a-production-system
计费逻辑从主流程解耦,用事件驱动处理“脏数据”,这个方案务实而优雅。初创期过度设计是陷阱,把side effect隔离到异步worker里,既保持核心简洁又留足扩展空间。真正的好架构,往往就是这样少写代码、多想边界。https://blog.exe.dev/billable-facts
GitHub 终于把 Stacked PRs 做进了原生体验,不再靠 CLI hack 硬撑。它将大型变更拆成可独立审查的小块,深度集成分支保护与合并队列,让代码审查从串行阻塞变成并行流水线。对团队协作和主干稳定性来说,这是务实且影响深远的工程优化,值得立刻尝试。https://github.blog/changelog/2026-07-30-stacked-pull-requests-are-now-in-public-preview/
❤1
Zig 与 QBE 的搭配,是对 LLVM 臃肿的一次务实减法。这篇从词法到原生代码的完整演示,不只补了编译教程的缺,更在工具链选型上给出轻量思路。团队有人说“不适合生产”,但把底层复杂度降下来,本身就是在为语言创新腾出空间。推荐给厌倦堆砌、偏爱简洁的架构者。https://tomekw.com/overengineered-calculator-zig-qbe/
按钮与链接的语义混淆是前端体验的慢性病。这篇文章从无障碍与可预测交互切入,直指 `<a>` 当按钮的病灶,提案用 `action` 属性让动作回归“不可重定向”的本质。团队成员改语义后点击率涨12%的案例,证明小细节撬动大转化。推荐每位前端细读,多思考,少写糊弄的代码。https://unplannedobsolescence.com/blog/buttons-vs-links/
从React迁回Htmx,这事看着像“返祖”,实则把论坛类软件的交互本质算明白了——大部分页面不需要全局状态机,局部替换就够了。小前说这是“开发者体验的文艺复兴”,我更看重它省掉的构建步骤和维护负担。少写代码,多思考架构,这才是长期主义的务实选择。https://misago-project.org/t/removing-reactjs-from-the-codebase-and-adapting-htmx-for-ui-interactivity/1267/
SQLite WAL 模式的这个坑,我们已经踩过。短命读连接在极端场景下触发排他锁,量化为可复现的错误,这远不止是文档上的一行提醒。作者没有停留在解释,而是给出了明确的 trade-off 和回退 DELETE 的决策路径——这才是架构师需要的深度。如果你也在高频小事务场景中用 SQLite,值得花五分钟认真读读这篇。https://hynek.me/til/sqlite-read-only-wal-locked/
Showing the 12 most recent of 21 posts we hold for @cndevdaily. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Citation-graph rank
Citation-graph rank — 1,073,359 of 1,478,351entries in the measured graph. A weighted position computed from the forward and mention edges below — republished posts weigh more than named mentions — and recomputed periodically, over the whole graph. Published only as this ordinal position, never as a score: a position is a fact, and a score printed beside one channel’s name would read as a verdict this register does not make. The two counts beneath stay separate for the same reason mentions are never summed with forwards anywhere else on this page — a named-by count costs nothing to manufacture. The top 100 by this measure, or how it is computed.
Forward network
Republished by
Channels on the register that have forwarded this channel's posts into their own feed.
Built only from forwarded posts we have actually read, on both sides. Coverage is early and deliberately incomplete: a missing link means we have not read the post that would prove it, never that the relationship does not exist. Counts are distinct forwarded posts observed, so they only ever go up as we read more.
Mentions
Named by 1 registered channel — every channel on the register whose own posts have named this one, by its current username or any other username it currently holds, merged from two separately captured readings of the same fact so a namer caught by only one of them is not missed and a namer both caught is not counted twice. A username this channel has since dropped is not matched — that handle may belong to someone else now, and crediting today’s namer to yesterday’s owner would misattribute it.
Named by
Channels on the register whose posts name this channel's handle.
A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.
Cite this entry
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 13 August 2026 — this entry's latest reading, not the date you are reading this.
“开发者日报” (@cndevdaily), 1,932 subscribers as measured 13 August 2026. Telegram Register, tgregister.com/channel/cndevdaily.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.