G

MadGoatHaz

·

AI & ML interests

None yet

Recent Activity

updated a collection 6 days ago

Qwen3.8-Flash-Next

updated a collection 6 days ago

new activity 16 days ago

jamesbrunet/Swift-Qwen3.8-27b-W4A16-AutoRound:MTP head fails to load in vLLM: mtp.* linears missing from quantization_config.ignore

View all activity

Organizations

None yet

New activity in jamesbrunet/Swift-Qwen3.8-27b-W4A16-AutoRound 16 days ago

MTP head fails to load in vLLM: mtp.* linears missing from quantization_config.ignore

#2 opened 17 days ago by

New activity in Vishva007/Qwen3.8-27B-W4A16-AutoRound-GPTQ about 1 month ago

Hands down the best Ampere Qwen3.8-27B quant available — by a long shot.

#2 opened about 1 month ago by

Issue & Fix: vLLM Speculative Decoding (MTP) Fails Due to Quantized Draft Head

#1 opened about 1 month ago by

New activity in Frozenlock/Qwen3.8-27B-int4-AutoRound about 1 month ago

Great stuff on Ampere

#2 opened about 1 month ago by

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B-FP8 3 months ago

Deployment Note: vLLM JIT Path Resolution -nvidia/cu13/lib/-

#5 opened 3 months ago by

Fix for vLLM Loading Crash on Ampere/Ada GPUs (TP=8, RuntimeError: size_n = 12)

#2 opened 3 months ago by

vllm loaded with error

#1 opened 3 months ago by

New activity in Xingyu-Zheng/Qwen3.6-27B-INT8-FOEM 5 months ago

MTP not accepting tokens

#1 opened 5 months ago by

MTP not accepting tokens

#1 opened 5 months ago by