Chris Scott
chriswritescode
AI & ML interests
None yet
Recent Activity
liked
a model
4 days ago
Qwen/Qwen-Image-Edit
new activity
16 days ago
openai/gpt-oss-120b:Request: 4-bit GPTQ or AWQ quantized version of openai/gpt-oss-20b
new activity
17 days ago
openai/gpt-oss-120b:VLLM - Flash-attn 3
Organizations
None yet
Request: 4-bit GPTQ or AWQ quantized version of openai/gpt-oss-20b
🚀
❤️
12
12
#32 opened 17 days ago
by
powtac
VLLM - Flash-attn 3
12
#23 opened 17 days ago
by
chriswritescode
Please make one for the larger Non Air Variant
3
#2 opened 24 days ago
by
chriswritescode
AWQ 4Bit / GPTQ with full precision gates and head? Please
8
#4 opened 25 days ago
by
chriswritescode
Qwen3-235B-A22B-Instruct-2507, int4-w4a16 or awq? Which one has better accuracy recovery?
1
#1 opened 27 days ago
by
traphix
Type of quantization
3
#1 opened about 1 month ago
by
systemicAnomaly
Quantization Config
1
#2 opened 29 days ago
by
chriswritescode
quantization method?
1
#2 opened 29 days ago
by
chriswritescode
VLLM
1
#1 opened about 1 month ago
by
chriswritescode
Tool support? Multiple tool calls?
#1 opened about 2 months ago
by
chriswritescode
Fast tokenizer, general VLLM support
2
#5 opened about 2 months ago
by
chriswritescode
Tool calling parser?
2
#11 opened about 2 months ago
by
sguo35
VLLM docker deployment
2
#4 opened about 2 months ago
by
chriswritescode
other models
2
#1 opened 2 months ago
by
scotto2
Yarn context
3
#3 opened 3 months ago
by
chriswritescode
Quantization question
3
#1 opened 3 months ago
by
cruzanstx
I get errors trying to deploy this in vllm or sglang.
😔
👍
7
3
#1 opened 3 months ago
by
chriswritescode
VLLM, SGLANG
7
#1 opened 4 months ago
by
chriswritescode
How was this made? Quant configuration? Have you deployed this with SGLANG or vllm ?
1
#1 opened 4 months ago
by
chriswritescode
Slow inference on vLLM
3
#1 opened 4 months ago
by
hp1337