eepos
eepos
AI & ML interests
None yet
Recent Activity
liked a dataset 1 day ago
Lakonik/t2i-prompts-3m liked a model 1 day ago
unsloth/DeepSeek-V4-Flash-GGUF liked a model 2 days ago
comfyanonymous/int4_testsOrganizations
None yet
Flash attention optimization for significant speedup. - old title: Optimization tips to maximize generation speed?
16
#6 opened about 1 month ago
by
eepos
Gemma-4 QAT Special Unsloth quants
β€οΈ 4
9
#1 opened about 1 month ago
by
danielhanchen
Nvfp4 vs nf4
5
#3 opened about 1 month ago
by
realrebelai
do we need both models
9
#1 opened about 1 month ago
by
ryg81
NEW MTP for Step 3.5 / 3.7 in Lama b9480
4
#6 opened about 1 month ago
by
Nerdsking
approvals
π 8
14
#1 opened 2 months ago
by
cudaoom
What is difference between fp8 scaled and mxfp8?
7
#4 opened 2 months ago
by
shivshankar
4bpw request =)
π 1
13
#2 opened 3 months ago
by
BahamutRU
What file do I need to download for Flux 2 Klein 9B π€
π 1
13
#2 opened 3 months ago
by
Hearcharted
Very nice loRA
2
#1 opened 6 months ago
by
mjimmer
Why is this happening?
33
#2 opened 6 months ago
by
Liquidmind111
LoRA Key discussion
π€― 2
5
#2 opened 6 months ago
by
ByteZSzn
error on Comfy UI
β 4
1
#1 opened 7 months ago
by
BetinhoFormado
ComfyUI compatibility
π 1
1
#1 opened 7 months ago
by
eepos
torch.compile needs frequent recompiles. Any tips?
π 1
#8 opened 8 months ago
by
eepos
Generates a black image
2
#2 opened 8 months ago
by
Disya
ArliAI/GLM-4.5-Air-Derestricted
2
#1561 opened 8 months ago
by
eepos
How to use fp8 mat-mul?
8
#7 opened 11 months ago
by
Muawiz