Juan Calderon-Perez

g-a-b-y's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in vllm-sr/d3 16 days ago

Quantized version for vLLM support

👀 1

9

#2 opened 25 days ago by

BuiDoan

New activity in zai-org/GLM-5.3-Flash 24 days ago

Please map reasoning effort levels

7

#41 opened 2 months ago by

g-a-b-y

New activity in RedHatAI/GLM-5.3-Flash-NVFP4 about 2 months ago

Missing RedHatAI/GLM-5.3-NVFP4

2

#5 opened about 2 months ago by

g-a-b-y

New activity in nvidia/Qwen3.8-Flash-Next-NVFP4 about 2 months ago

Quant requests?

2

#5 opened 2 months ago by

pathosethoslogos

New activity in RedHatAI/GLM-5.2-speculator.dspark about 2 months ago

Works for me

12

#3 opened 3 months ago by

ehartford

New activity in zai-org/GLM-5.3-Flash about 2 months ago

Model output issues

👀 1

48

#23 opened 2 months ago by

fabric

[BUG] Reasoning Loop on Trivial Task

10

#47 opened about 2 months ago by

voves

New activity in nvidia/GLM-5.3-Flash-NVFP4 about 2 months ago

MTP layers missing?

3

#1 opened about 2 months ago by

g-a-b-y

New activity in RedHatAI/GLM-5.3-Flash-NVFP4 about 2 months ago

Dspark speculator?

👍 3

2

#2 opened 2 months ago by

Lanchou

New activity in incoai/GLM-5.3-Flash-DFlash2 about 2 months ago

Missing vLLM support

#5 opened about 2 months ago by

g-a-b-y

New activity in RedHatAI/Qwen3.8-27B-INT4 2 months ago

Doesn't have FP8 VLLM KVCache calibration scales

➕ 1

3

#3 opened 2 months ago by

ibaldonl

New activity in RedHatAI/GLM-5.3-Flash-NVFP4 2 months ago

Support for NVFP4 kv cache

#3 opened 2 months ago by

g-a-b-y

New activity in incoai/GLM-5.3-Flash-DFlash2 2 months ago

Base model requirements

#4 opened 2 months ago by

g-a-b-y

New activity in RedHatAI/Qwen3.8-27B-INT4 2 months ago

Friggin AWESOME quant of a GREAT model.

👍❤️ 6

3

#2 opened 2 months ago by

Bellesteck

New activity in RedHatAI/GLM-5.2-speculator.dspark 2 months ago

Failed to run on 8xB200 - AssertionError: Tried to load weights of size torch.Size([6144, 30720])to a parameter of size torch.Size([6144, 18432])

12

#1 opened 3 months ago by

shakhizat

New activity in inclusionAI/Ling-3.0-flash-dspark 2 months ago

vLLM Support

1

#2 opened 2 months ago by

g-a-b-y

New activity in froggeric/Qwen-Fixed-Chat-Templates 3 months ago

v22.3 release notes

👍🔥 8

8

#85 opened 3 months ago by

froggeric

v22.3: Error detection tiering, reasoning fixes, test suite 44→101 + property fuzzer

5

#84 opened 3 months ago by

g-a-b-y

New activity in RadixArk/Qwen3.8-27B-DSpark 3 months ago

[BUG] DSpark slower than EAGLE + severe cold-start penalty

7

#3 opened 3 months ago by

voves

New activity in Qwen/Qwen3.8-27B 3 months ago

No multimodal on vLLM? Model Qwen/Qwen3.8-27B-FP8 is treated as multimodal but has no registered multimodal processor; running in text-only mode.

1

#146 opened 3 months ago by

pabbbb