Dipika
AI & ML interests
I work on LLM Compressor, Compressed-Tensors and Speculators
Recent Activity
liked a model 2 days ago
RedHatAI/Qwen3.8-27B-MXFP4 updated a model 2 days ago
RedHatAI/Qwen3.8-27B-MXFP4 updated a model 2 days ago
RedHatAI/GLM-5.3-Flash-NVFP4Organizations
License metadata missing — is this Apache-2.0?
👍 1
1
#1 opened 16 days ago
by
mason17
Missing RedHatAI/GLM-5.3-NVFP4
1
#5 opened 4 days ago
by
g-a-b-y
Corrections to the chat template (Taken from the original repo)
1
#4 opened 16 days ago
by
FredyRivera-dev
Doesn't have FP8 VLLM KVCache calibration scales
➕ 1
3
#3 opened 18 days ago
by
ibaldonl
on RTX 3090
1
#1 opened 5 months ago
by
faheemraza1
Impossible to deploy using vLLM 0.20.0
3
#6 opened 5 months ago
by
hdnh2006
Why is max-model-len 96000?
1
#2 opened 5 months ago
by
RickRossTN
Gemma 4 NVFP4
#10 opened about 1 month ago
by
Zek-Takai
Dspark speculator?
👍 3
2
#2 opened 23 days ago
by
Lanchou
Friggin AWESOME quant of a GREAT model.
👍❤️ 5
3
#2 opened 25 days ago
by
Bellesteck
MTP layer 45 weights are missing from the checkpoint
2
#1 opened 23 days ago
by
colabbear
MTP/Dflash/Dspark support
2
#1 opened about 1 month ago
by
g-a-b-y
Update config.json
#19 opened about 1 month ago
by
dsikka
Update non-thinking chat template
#3 opened 3 months ago
by
agesf
Update non-thinking chat template
#3 opened 3 months ago
by
agesf
Update README.md
#1 opened 3 months ago
by
lwilkinson
Update README.md
#1 opened 3 months ago
by
lwilkinson
Update chat_template.jinja
#6 opened 4 months ago
by
bdellabe
Update chat_template.jinja
#8 opened 4 months ago
by
bdellabe
Update chat_template.jinja
1
#4 opened 5 months ago
by
bdellabe