Zheng Han
traphix
·
AI & ML interests
None yet
Recent Activity
liked
a model
about 16 hours ago
RedHatAI/Qwen3-Next-80B-A3B-Instruct-quantized.w4a16
new activity
about 16 hours ago
RedHatAI/Qwen3-Next-80B-A3B-Instruct-quantized.w4a16:Tokenizer you are loading with an incorrect regex pattern
new activity
about 1 month ago
Intel/Qwen3-Next-80B-A3B-Instruct-int4-AutoRound:Failed to find a kernel that can implement the WNA16 linear layer
Organizations
None yet
Tokenizer you are loading with an incorrect regex pattern
1
#2 opened about 1 month ago
by
traphix
Failed to find a kernel that can implement the WNA16 linear layer
#1 opened about 1 month ago
by
traphix
vllm error: Extra inputs are not permitted
#1 opened about 1 month ago
by
traphix
Can A100 run Qwen3-235B-A22B-Instruct-2507-NVFP4?
#1 opened about 2 months ago
by
traphix
Error on 4 x L40s
➕
2
1
#4 opened 4 months ago
by
traphix
I got ValueError
👀
2
10
#3 opened 4 months ago
by
spow12
How to run this model via vllm？
11
#2 opened 4 months ago
by
traphix
FP8 please
👀
➕
16
8
#18 opened 4 months ago
by
aliquis-pe
vllm v0.10.2 error
❤️
1
#2 opened 4 months ago
by
traphix
VLLM compatibility?
9
#1 opened 4 months ago
by
aidendle94
Instruct or Thinking?
#1 opened 4 months ago
by
traphix
Could you share your quantization code？
1
#1 opened 4 months ago
by
traphix
Instruct or thinking？
#1 opened 4 months ago
by
traphix
Any plans to quantize Qwen3-235B-A22B-Instruct-2507？
#1 opened 5 months ago
by
traphix
Qwen3-235B-A22B-Instruct-2507, int4-w4a16 or awq? Which one has better accuracy recovery?
1
#1 opened 6 months ago
by
traphix
Does vllm 0.7.3 support this model？
1
#10 opened 11 months ago
by
traphix
Any plans to quantize Qwen3-235B-A22B-Instruct-2507？
#1 opened 6 months ago
by
traphix
Is 4 x H20 96G sufficient to run this model?
2
#2 opened 8 months ago
by
milongwong
Remove vLLM FP8 Limitation
10
#2 opened 9 months ago
by
simon-mo
Error running on A100?
2
#4 opened 9 months ago
by
traphix