Pinned Tweet
助力一下 gopher 今年金九银十跳槽季,小弟我把去年刷的 leetcode 整理出了 520 题汇成了小册子,全部都是 go 实现的 runtime beats 100% 了。在线阅读地址:books.halfrost.com/leetcode/,网页支持了 PWA,可以像 mac 应用一样沉浸式阅读。@chaishushan
@changkun @talkgo_night @unknwon @astaxie
vLLM V1, part 7: Automatic Prefix Caching. Chained block hashes find reusable prefixes; only finalized full blocks enter the cache; the free queue doubles as lazy LRU. github.com/halfrost/Halfrost…
I traced vLLM V1’s KV cache from GPU budget to physical slot: fixed-size blocks, prefix hashes, refcounts, preemption, and block tables. Part 6: github.com/halfrost/Halfrost…
1
524
vLLM V1 has no global “prefill phase” or “decode phase.”
Each step asks: how many tokens may each request process?
Article 05 traces token budgets, RUNNING-before-WAITING, Chunked Prefill, prefix-aware admission & KV-pressure preemption.
github.com/halfrost/Halfrost…
#vLLM
3
8
1,086
vLLM’s heartbeat is EngineCore.step():
schedule → execute → abort barrier → commit
Article 04 traces request states, overlapped batches, optimistic counters, aborts, cleanup & continuous batching—one tick, line by line.
github.com/halfrost/Halfrost…
#vLLM
vLLM V1 is not “an API server calling a GPU.”
It is a process topology:
API server → ZMQ → EngineCore → shared-memory queues → GPU workers.
Article 03 traces GIL isolation, TP/DP math, startup barriers, and worker-death propagation.
github.com/halfrost/Halfrost…
#vLLM
2
5
748
vLLM has 3 front doors: LLM.generate(), vllm serve, and OpenAI-compatible HTTP.
Follow the source and they converge:
process_inputs → EngineCoreRequest → EngineCore.
Article 02 traces offline, CLI, HTTP, SSE & cancellation.
github.com/halfrost/Halfrost…
#vLLM
6
661
What happens between LLM.generate() and the first token returned by vLLM? I traced the complete V1 request path—from input processing and continuous-batch scheduling to GPU execution, sampling, and output processing.
Part 1 of a source-code walkthrough:
github.com/halfrost/Halfrost…
8
564
My GitHub Sponsors profile is live! You can sponsor me to support my open source work 💖 github.com/sponsors/halfrost…
2
19
谢谢 luolei 老师,您也是我一直学习的榜样!一起加油,与君共勉💪🏻
今天看到一个认识多年的朋友的朋友圈,这个浮躁的世界,值得学习和共勉。刚认识这朋友时,他还是饿了么的前端,一路到写 iOS,写 Go,一直坚持学习和输出,去年得知他考到美帝 CMU。👍 @halffrost
I updated my GitHub Profile very carefully, making a new header for the new year, updating the technology I am currently learning and the books I am reading. Wish everyone a Merry Christmas 🎉.
10K followers milestone. Thank you for sending me birthday presents in advance on the day of 520. I hope I can become a Go Contributor this year or next year. 🙏🏻
什么是树状数组?如果你想知道,什么是树状数组的话,我现在就带你研究!books.halfrost.com/leetcode/…
(最近又重新开始写点算法相关的文章了,自己梳理知识点的过程中也顺带增加一下 《LeetCode Cookbook》的知识厚度吧🤪)
《深入研究 Go interface 底层实现》:github.com/halfrost/Halfrost…
整体代码都是基于 plan9 的汇编代码。plan9 可读性还比较好,理解起来不复杂。这篇文章里面主要是内存地址,汇编代码比较枯燥,其他的内容理解起来不难。欢迎大家指教🙏🏻























