[ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".
active 2024-10-04 → 2026-05-25 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 599 days from 2024-10-04 to 2026-05-25. Pushes: 22 total, peak 7 in a day. Pull requests: 3 total, peak 2 in a day. Issues: 24 total, peak 3 in a day. Comments: 21 total, peak 3 in a day. Stars: 125 total, peak 10 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 |
|---|---|---|---|---|
| Gumpest | 38 | 22 | 1 | 11 |
| Yxxxb | 4 | 0 | 0 | 1 |
| fode-design | 2 | 0 | 0 | 1 |
| sihany077 | 2 | 0 | 0 | 0 |
| naajeehxe | 2 | 0 | 0 | 0 |
| Naive-Bayes | 2 | 0 | 0 | 1 |
| 924973292 | 2 | 0 | 0 | 0 |
| Man-PaperRejected | 1 | 0 | 0 | 1 |
| Dayoung-Kil | 1 | 0 | 0 | 0 |
| liuting20 | 1 | 0 | 0 | 0 |
| UnableToUseGit | 1 | 0 | 0 | 1 |
| YuchenLiu98 | 1 | 0 | 0 | 0 |
| hsv-tse-kun | 1 | 0 | 0 | 0 |
| Cooperx521 | 1 | 0 | 0 | 1 |
| xiaonengmiao | 1 | 0 | 0 | 1 |
| KaKa-101 | 1 | 0 | 0 | 0 |
| ylnxxts | 1 | 0 | 1 | 0 |
| SKY072410 | 1 | 0 | 0 | 0 |
| YUECHE77 | 1 | 0 | 0 | 1 |
| leofan90 | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#34Dayoung-Kil2026-02-12 03:49Question about FLOPs and Latency Measurement (Table 1)
- Issue comment#8fode-design2026-01-08 08:54Could you please provide the code for efficiency analysis in Table 4?
- Issue#32fode-design2026-01-07 04:06What is the specific calculation formula for latency (ms/token)? Is it only the decoding time that needs to be calculated, or does the pre-filling time also need to be taken into account?
- Issue#31Sukidat2025-12-21 07:15VideoLlava环境
- Issue comment#26oPresent2025-12-14 11:56Compatibility with FlashAttention
- ReleaseGumpest2025-12-12 02:38SparseVLM+
- Issue#28panxuyan2025-11-08 06:34P100 support?
- Issue#22Gumpest2025-09-26 02:48How to obtain visualization results in Figure 6?
- Issue comment#24Gumpest2025-09-26 02:46Could you please clarify the detailed meaning and computing method of "equal token num until now: 192.03125 ,total_layers_cuda_time:56175.52429199219,TFLOPs_avg_sample:1.8177142649287112"?
- Issue#24Gumpest2025-09-26 02:46Could you please clarify the detailed meaning and computing method of "equal token num until now: 192.03125 ,total_layers_cuda_time:56175.52429199219,TFLOPs_avg_sample:1.8177142649287112"?
- Issue#12Gumpest2025-09-26 02:45Correction of the accuracy of FastV
- Issue comment#16xiaonengmiao2025-09-25 08:19other benchmark eval code
- Issue comment#12Man-PaperRejected2025-08-15 08:20Correction of the accuracy of FastV
- Issue#259249732922025-07-12 06:50Why the inference speed is extremely slower than the normal state? e.g. normal 5 mins on MME but SparseVLMs takes about 1 h?
- Issue#249249732922025-07-11 03:46Could you please clarify the detailed meaning and computing method of "equal token num until now: 192.03125 ,total_layers_cuda_time:56175.52429199219,TFLOPs_avg_sample:1.8177142649287112"?
- Issue#2Gumpest2025-06-04 08:04About Video Understanding
- Issue comment#23Gumpest2025-06-04 07:57Upload SparseVideoLLaVA
- Pull request#23Gumpest2025-06-04 07:57
- Pull request#23leofan902025-06-04 07:35
- Issue comment#2kinredon2025-05-24 04:37About Video Understanding
- Issue#20zhuyglx2025-04-27 09:41SparseVLMs 能用在 qwen2.5-vl系列吗
- Issue comment#18Gumpest2025-04-15 04:03I wonder how I can evaluate a model with lmms_eval
- Issue comment#13Gumpest2025-04-15 04:00use the SparseVLMs in another MLLM
- Pull request#19ylnxxts2025-03-02 10:55
- Issue#17KaKa-1012024-12-24 08:04How to calculate the true used token numbers?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 125 stars here means stars gained during the window, not the repo's star count.