Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
dstair
/
qwen3.5-moe-fp8-trainium2
Like
0
aws-trainium
aws-neuron
nki
fp8
mixture-of-experts
quantization
qwen
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
qwen3.5-moe-fp8-trainium2
95.8 kB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
dstair
Add runnable FP8 MoE weight-prep example
6f379bf
verified
about 2 months ago
examples
Add runnable FP8 MoE weight-prep example
about 2 months ago
kernels
Trim to the shipped block_ob_coalesced path (match gated-deltanet-nki-trainium)
about 2 months ago
.gitattributes
Safe
1.52 kB
initial commit
about 2 months ago
LICENSE
Safe
11.4 kB
Add Trn2 FP8 loader + fused MoE NKI kernel for Qwen3.5-35B-A3B-FP8
about 2 months ago
NOTICE
Safe
793 Bytes
Add Trn2 FP8 loader + fused MoE NKI kernel for Qwen3.5-35B-A3B-FP8
about 2 months ago
README.md
Safe
5.53 kB
Add runnable FP8 MoE weight-prep example
about 2 months ago
moe_w8.py
Safe
17.3 kB
Trim to the shipped block_ob_coalesced path (match gated-deltanet-nki-trainium)
about 2 months ago
st_reader.py
Safe
2.82 kB
Add Trn2 FP8 loader + fused MoE NKI kernel for Qwen3.5-35B-A3B-FP8
about 2 months ago
