Retrieval LLM
active 2023-12-19 → 2026-02-26 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 801 days from 2023-12-19 to 2026-02-26. Pushes: 39 total, peak 6 in a day. Pull requests: 6 total, peak 2 in a day. Issues: 61 total, peak 10 in a day. Comments: 80 total, peak 11 in a day. Stars: 355 total, peak 39 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 |
|---|---|---|---|---|
| zheyishine | 68 | 29 | 2 | 26 |
| chenliangjyj | 31 | 10 | 0 | 15 |
| jivanph | 9 | 0 | 0 | 6 |
| nrmer | 7 | 0 | 0 | 0 |
| May-Yaha | 6 | 0 | 0 | 4 |
| AGI-Jarvis | 6 | 0 | 0 | 4 |
| shinerdeng | 5 | 0 | 0 | 3 |
| ZipECHO | 5 | 0 | 0 | 5 |
| 2065037421 | 4 | 0 | 0 | 0 |
| Vithulep | 4 | 0 | 0 | 1 |
| learning-chip | 4 | 0 | 0 | 3 |
| janelu9 | 4 | 0 | 0 | 2 |
| xiningnlp | 4 | 0 | 0 | 1 |
| snippetzero | 2 | 0 | 0 | 1 |
| dafen12 | 2 | 0 | 0 | 1 |
| yuenyu1 | 2 | 0 | 0 | 0 |
| gigigigig1 | 2 | 0 | 0 | 1 |
| MeJerry215 | 2 | 0 | 0 | 1 |
| Mewo518 | 2 | 0 | 2 | 0 |
| bhpugongying | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#45zlH5182025-11-08 17:13fix: add cleanup method for clean the processes
- Pull request#40hjyai942025-09-28 07:30
- Issue comment#39zheyishine2025-04-23 06:17Looking forward to the flood paper since offline is sort of being ignored currently, when will u post it?
- Issue#39cvtower2025-04-21 03:08Looking forward to the flood paper since offline is sort of being ignored currently, when will u post it?
- Pull request#38Mewo5182025-04-17 05:14
- Pull request#38Mewo5182025-04-17 05:08
- Issue#37bhpugongying2025-04-16 03:39您好，请问lookahead现在支持Qwen2.5吗？
- Issue comment#36zheyishine2025-04-01 11:31I'm unable to replicate the experimental results presented in the paper.
- Issue comment#36gigigigig12025-03-28 06:42I'm unable to replicate the experimental results presented in the paper.
- Issue#36gigigigig12025-03-28 02:55I'm unable to replicate the experimental results presented in the paper.
- Issue#3520650374212025-03-15 10:47triton.runtime.errors.OutOfResources
- Issue#3420650374212025-03-15 10:47'LLM' object has no attribute 'stream_generate'
- Issue comment#35zheyishine2025-03-14 07:22triton.runtime.errors.OutOfResources
- Issue#3520650374212025-03-12 11:53triton.runtime.errors.OutOfResources
- Issue#3420650374212025-03-12 07:59'LLM' object has no attribute 'stream_generate'
- Pull request#33zheyishine2025-03-08 09:48
- Issue comment#32Vithulep2025-03-07 09:02Output of llma-2-7b model is repetative.
- Issue#9zheyishine2025-03-06 13:10In the benchmark studies, how are the draft tokens generated?
- Issue comment#9zheyishine2025-03-06 13:10In the benchmark studies, how are the draft tokens generated?
- Issue#22zheyishine2025-03-06 13:09Changing naive attention to SDPA gives wrong result for batched llama example
- Issue#13zheyishine2025-03-06 13:09Consider Support CodeLlama?
- Issue#23zheyishine2025-03-06 13:08AntRAG
- Issue comment#20zheyishine2025-03-06 13:08是否支持Qwen 1.5?
- Issue#20zheyishine2025-03-06 13:08是否支持Qwen 1.5?
- Issue#24zheyishine2025-03-06 13:07Do lookahead and repetition_penalty conflict?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 355 stars here means stars gained during the window, not the repo's star count.