Skip to content

DFloat11: Lossless LLM Compression for Efficient GPU Inference

active 2025-04-182026-05-12 (UTC)

Partial coverage17,073 / 21,774 hourly files (78%) · 2 absent upstream · 4,700 failed, retryable2024-02-172026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
446
Pushes
6
Pull requests
2
Issues
28
Stars
328
Forks
20

Activity over time

Daily event counts in the loaded window

Line chart, 390 days from 2025-04-18 to 2026-05-12. Pushes: 6 total, peak 2 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 28 total, peak 2 in a day. Comments: 61 total, peak 6 in a day. Stars: 328 total, peak 77 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

ContributorContributionsPushesPRsComments
tonyzhang617346222
mingyi456140011
Andy04223002
unquietwiki3002
pramodith3001
ehartford3002
Luwill62001
Bruhmement2001
kabachuha2002
whatever19832002
amosyou2001
Manni10002001
calanquee2000
sankexin2001
mitkox2000
MeiYi-dev1000
LatentSpacer1001
win10ogod1000
animemory1000
BigBIueWhale1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#35erusiamu2026-05-05 11:24
    Request update for Cuda13 compatibility
  • Issue comment#37mingyi4562026-03-16 07:38
    Apply Bfloat11 to activation
  • Issue comment#37mingyi4562026-03-16 06:58
    Apply Bfloat11 to activation
  • Issue comment#37jhy20k2026-03-16 06:25
    Apply Bfloat11 to activation
  • Issue#36calanquee2026-02-07 09:47
    [Performance] Significant Decompression Throughput Degradation on GPU 0 and when using CUDA_VISIBLE_DEVICES (H200 HGX)
  • Issue#36calanquee2026-02-06 08:04
    [Performance] Significant Decompression Throughput Degradation on GPU 0 and when using CUDA_VISIBLE_DEVICES (H200 HGX)
  • Issue#34matalama80td3l2026-01-16 10:39
    Request for DFloat11 Quantization Support for FLUX.2-klein-9B and FLUX.2-klein-base-9B Model
  • Issue comment#15zji9962025-12-17 10:03
    Can it be compatible with other quantization models such as fp8, int4, and models like Gapeleon/bytedance-BAGEL-7B-MoT-INT8 to reduce their memory usage
  • Issue comment#15mingyi4562025-12-16 08:34
    Can it be compatible with other quantization models such as fp8, int4, and models like Gapeleon/bytedance-BAGEL-7B-MoT-INT8 to reduce their memory usage
  • Issue#33jaxiez2025-11-18 06:29
    Converted DFloat11 shards into safetensors for ComfyUI
  • Issue#32mingyi4562025-11-03 17:34
    Feature request: support for decompressing `nn.Conv2d` (and similar) tensors
  • Issue#30tonyzhang6172025-09-30 04:25
    DF11 for Qwen-Image-Edit-2509 (make it fit on 32 GB 🤝)
  • Issue#30BigBIueWhale2025-09-23 15:17
    DF11 for Qwen-Image-Edit-2509 (make it fit on 32 GB 🤝)
  • Issue comment#29mingyi4562025-09-22 12:36
    qwen-image-edit load error
  • Issue comment#29Luwill62025-09-22 11:39
    qwen-image-edit load error
  • Issue comment#29mingyi4562025-09-22 09:06
    qwen-image-edit load error
  • Issue comment#29mingyi4562025-09-22 07:01
    qwen-image-edit load error
  • Issue comment#22mingyi4562025-09-21 13:18
    Can we quantize the df11 model ourselves?
  • Issue#29Luwill62025-09-19 02:51
    qwen-image-edit load error
  • Issue comment#28mingyi4562025-09-18 17:46
    How to compress t5-v1_1-xxl and Gemma-2-2B?
  • Issue comment#28mingyi4562025-09-18 04:55
    How to compress t5-v1_1-xxl?
  • Issue comment#28mingyi4562025-09-17 17:24
    How to compress t5-v1_1-xxl?
  • Issue#28mingyi4562025-09-14 12:03
    How to compress t5-v1_1-xxl?
  • Issue#24tonyzhang6172025-08-28 07:49
    could you please support bagel?
  • Issue comment#27tonyzhang6172025-08-28 07:48
    How do load DF11 models in `diffusers` without the original transformer weights?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 328 stars here means stars gained during the window, not the repo's star count.