ElliotGao

tclf90's activity

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

New activity in QuantTrio/Kimi-K3-Cubic-2.5Bit about 11 hours ago

benchmark data for Kimi-K3-Cubic-2.5Bit

2

#2 opened 9 days ago by

bencswong2

New activity in QuantTrio/Kimi-K3-Cubic-2.5Bit 8 days ago

佈署失敗 (ó﹏ò｡)

4

#4 opened 8 days ago by

gold9450412

Roadmap for DSpark support in the Cubic vLLM branch?

2

#3 opened 9 days ago by

bencswong2

New activity in QuantTrio/GLM-5.2-Int4-Int8Mix about 2 months ago

GLM-5.2-Int4-Int8Mix generates only "!!!!!" on H100 8×80GB with vLLM 0.23.0/0.24.0 — IndexShare sparse indexer K-cache never populated during prefill

4

#3 opened about 2 months ago by

kinggenguo

AWQ 4bit

2

#2 opened about 2 months ago by

MatthieuZ

New activity in QuantTrio/GLM-4.7-AWQ 3 months ago

Revert remplate

#8 opened 3 months ago by

s-yanev

Support for structured output

#7 opened 3 months ago by

s-yanev

New activity in QuantTrio/DeepSeek-V3.1-AWQ-Lite 3 months ago

Fix chat_template crash when assistant message omits the `content` key

#5 opened 3 months ago by

qgallouedec

New activity in QuantTrio/DeepSeek-V3.2-Exp-AWQ 3 months ago

Fix chat_template crash when assistant message omits the `content` key

#4 opened 3 months ago by

qgallouedec

New activity in QuantTrio/DeepSeek-V3.1-AWQ 3 months ago

Fix chat_template crash when assistant message omits the `content` key

#5 opened 3 months ago by

qgallouedec

New activity in QuantTrio/Qwen3.6-35B-A3B-AWQ 4 months ago

Any plans for a calibration-based AWQ build for better long-context stability?

2

#6 opened 4 months ago by

hyunw55

PPLX or KLD, or other benchmark

1

#4 opened 4 months ago by

HenkTenk

New activity in QuantTrio/GLM-5-AWQ 4 months ago

[Request] Great work! Do you have plans to also create GLM-5.1-AWQ?

🤗 1

10

#6 opened 4 months ago by

ag1988

New activity in QuantTrio/Qwen3.5-122B-A10B-AWQ 4 months ago

CUDA version 13?

1

#1 opened 4 months ago by

pathosethoslogos

New activity in QuantTrio/gemma-4-31B-it-AWQ 4 months ago

Request for awq of the gemma 4 26B A4B MoE

6

#1 opened 5 months ago by

rks2302

New activity in QuantTrio/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-AWQ 5 months ago

AWQ 4/5/6-bit request for Qwopus3.5-27B-v3

🚀❤️ 3

3

#2 opened 5 months ago by

celikburak

New activity in QuantTrio/Qwen3.5-27B-AWQ 5 months ago

AWQ 4-bit version of this Opus-Distilled-v2 model?

9

#5 opened 5 months ago by

celikburak

--max-model-len 32768 seems a bit too small for agent use cases ?

3

#3 opened 5 months ago by

edwarddukewu

New activity in QuantTrio/Qwen3.5-27B-AWQ 6 months ago

My personal vLLM launch cmd on my old personal 2x3090 workstation

7

#1 opened 6 months ago by

tclf90

New activity in QuantTrio/Qwen3.5-35B-A3B-AWQ 6 months ago

Can't get vLLM running on 1xRTX 4090

3

#1 opened 6 months ago by

slyfox1186