Python · active 2025-07-14 → 2026-05-11 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 302 days from 2025-07-14 to 2026-05-11. Pushes: 26 total, peak 4 in a day. Pull requests: 3 total, peak 1 in a day. Issues: 7 total, peak 1 in a day. Comments: 9 total, peak 2 in a day. Stars: 41 total, peak 4 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 |
|---|---|---|---|---|
| BlackSamorez | 22 | 18 | 1 | 3 |
| Godofnothing | 4 | 3 | 0 | 1 |
| songsm921 | 2 | 0 | 0 | 1 |
| ZhuYe0729 | 2 | 0 | 0 | 2 |
| Vahe1994 | 1 | 1 | 0 | 0 |
| llcnt | 1 | 0 | 0 | 0 |
| dingirsu | 1 | 0 | 0 | 1 |
| jackcook | 1 | 0 | 1 | 0 |
| JeffLee1874 | 1 | 0 | 0 | 0 |
| manyizhang | 1 | 0 | 0 | 0 |
| Superone77 | 1 | 0 | 0 | 0 |
| WeiweiZhang1 | 1 | 0 | 0 | 0 |
| faruknane | 1 | 0 | 0 | 1 |
| chkim1103 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#23chkim11032026-02-27 07:37Question: Any reason for not using random H matrix?
- Issue#22JeffLee18742026-02-03 07:16About default order implementation and performance
- Issue comment#19Godofnothing2025-12-11 11:19Regarding the Hadamard transform accuracy drop for nvfp4 with RTN in the paper
- Issue#17WeiweiZhang12025-11-25 02:15When using transformers.set_seed() instead of src.utils.common_utils.fix_seed(), openllm chat-template–related task accuracies drop to 0.
- Issue comment#16BlackSamorez2025-11-24 15:55BUG: Duplicate bias addition in PseudoQuant4x16NoMasterFn causes incorrect inference output
- Issue#16manyizhang2025-11-22 06:36BUG: Duplicate bias addition in PseudoQuant4x16NoMasterFn causes incorrect inference output
- Issue comment#15songsm9212025-11-21 08:05Realquant checkpoint vllm compatibility bug
- Pull request#14jackcook2025-11-14 20:51
- ReleaseBlackSamorez2025-10-28 13:36v0.3.2: Removed hadamard Randomness
- Pull request#12BlackSamorez2025-10-27 10:35
- Issue comment#5BlackSamorez2025-10-24 10:51Error in backward function
- Issue comment#10ZhuYe07292025-10-17 05:33Does nvfp4 inference be supported？
- Issue comment#10BlackSamorez2025-10-15 11:30Does nvfp4 inference be supported？
- Issue comment#10ZhuYe07292025-10-15 09:11Does nvfp4 inference be supported？
- Issue comment#7dingirsu2025-10-01 11:54GPTQ block quantization error implementation
- ReleaseBlackSamorez2025-09-30 13:10v0.2.0: FP-Quant Pre-Print Release
- Issue comment#8faruknane2025-09-22 13:42Evaluation Extremely Slow After Quantization
- Issue#7songsm9212025-09-22 03:26GPTQ block quantization error implementation
- Issue#5llcnt2025-08-27 15:59Error in backward function
- Issue#2Superone772025-07-26 08:26Environment & Dependency Information
- Pull request#1Godofnothing2025-07-24 07:39
- ReleaseBlackSamorez2025-07-22 12:34v0.1.6: better triton dispatch
- ReleaseBlackSamorez2025-07-18 11:50v0.1.4: no fast_hadamard_transform
- ReleaseBlackSamorez2025-07-14 09:57v0.1.1: Release kernel interfaces
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 41 stars here means stars gained during the window, not the repo's star count.