Disaggregated serving system for Large Language Models (LLMs).
active 2024-04-26 → 2026-04-27 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 732 days from 2024-04-26 to 2026-04-27. Pushes: 21 total, peak 4 in a day. Pull requests: 9 total, peak 2 in a day. Issues: 51 total, peak 3 in a day. Comments: 118 total, peak 19 in a day. Stars: 536 total, peak 6 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| interestingLSY | 31 | 6 | 1 | 18 |
| PKUFlyingPig | 28 | 7 | 3 | 13 |
| GindaChen | 12 | 8 | 0 | 3 |
| YLSnowy | 11 | 0 | 0 | 6 |
| KylinC | 9 | 0 | 1 | 5 |
| William12github | 7 | 0 | 0 | 6 |
| RobertLou | 6 | 0 | 0 | 5 |
| LordEdison | 6 | 0 | 0 | 6 |
| FuHaoTHU | 6 | 0 | 0 | 3 |
| TZHelloWorld | 5 | 0 | 0 | 3 |
| Dreamer-HIT | 4 | 0 | 0 | 3 |
| Liaukx | 4 | 0 | 1 | 2 |
| 67lc | 4 | 0 | 0 | 3 |
| vhch | 3 | 0 | 1 | 1 |
| wangguanggg | 3 | 0 | 0 | 1 |
| ddqspace-xyz | 3 | 0 | 0 | 3 |
| gursimar | 3 | 0 | 0 | 1 |
| irasin | 3 | 0 | 0 | 2 |
| Toseic | 3 | 0 | 1 | 1 |
| hyuenmin-choi | 3 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
- Issue#66Sabiha12252025-06-27 04:31'cudaMemcpy(ith_context_req_token_index.ptr, ith_context_req_token_index_cpu, sizeof(int32_t) * (batch_size+1), cudaMemcpyHostToDevice)'
- Issue comment#21YitaoYuan2025-05-21 06:14SwitfTransformer compilation fails with ambiguous conversion error at PyTorch 24.05 container.
- Issue#65Qiu-Jianrong2025-04-28 07:28关于论文引用的小小问题
- Issue comment#58Liaukx2025-04-24 06:16How to use DistServe with ray?
- Issue comment#58Haoyanlong2025-04-24 06:06How to use DistServe with ray?
- Issue#64Haoyanlong2025-04-23 09:25初始化的时候， 报错
- Issue comment#63LordEdison2025-04-17 10:44the inference result sentence is null
- Issue comment#59Mrxiangli2025-04-15 13:48How to handle preemption cases
- Issue comment#50Dreamer-HIT2025-04-08 14:35How to independently measure the performance of the Prefill phase and the Decode phase？
- Issue comment#63Dreamer-HIT2025-04-08 14:30the inference result sentence is null
- Issue comment#63LordEdison2025-04-08 14:20the inference result sentence is null
- Issue comment#63LordEdison2025-04-08 14:18the inference result sentence is null
- Issue comment#59Dreamer-HIT2025-04-08 13:17How to handle preemption cases
- Issue#63Dreamer-HIT2025-04-08 13:15the inference result sentence is null
- Pull request#62interestingLSY2025-04-06 15:54
- Issue comment#62interestingLSY2025-04-06 15:53Fix problem: use offline.py and Llama-2-7b-hf in a local directory
- Issue comment#10sjlgaga2025-04-06 10:15decoder.embed_tokens.weight.pt not found
- Pull request#62sjlgaga2025-04-06 10:13
- Issue comment#40LordEdison2025-03-26 07:47模型推理结果混乱，怎么解决。
- Issue comment#40LordEdison2025-03-17 12:49模型推理结果混乱，怎么解决。
- Issue#61HarryWu992025-03-17 09:41How to guarantee that kv cache transmission finished
- Issue comment#25LordEdison2025-03-09 17:52Swift transformers cmak build 一直循序
- Pull request#60Liaukx2025-02-28 03:46
- Issue comment#10Liaukx2025-02-28 02:45decoder.embed_tokens.weight.pt not found
- Issue#59Mrxiangli2025-02-26 22:48How to handle preemption cases
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 536 stars here means stars gained during the window, not the repo's star count.