Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
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
cfontes
/
glm53-spark-tp4
Like
3
Safetensors
glm_moe_dsa
glm
glm-5.3
exl3
Mixture of Experts
tensorfold
dgx-spark
kv-cache
prefix-caching
3-bit
License:
glm-5.3
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
glm53-spark-tp4
/
kv_cache
56.4 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
cfontes
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
dfc39f1
verified
9 days ago
README.md
Safe
5.27 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
apply.sh
Safe
1.68 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
patch_01_prefill_offset.py
Safe
4.89 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
patch_02_drafter_resume.py
Safe
4.09 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
patch_03_engine_wiring.py
Safe
3.2 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
patch_04_chunk_alignment.py
Safe
4.47 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
patch_05_fixed_chunks.py
Safe
2.68 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
patch_06_finalize.py
Safe
2.59 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
patch_07_canonical_end.py
Safe
2.98 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
prefix_cache.py
Safe
3.47 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
test_agentic.py
Safe
16.4 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
test_growth.py
Safe
1.45 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
test_semantic.py
Safe
1.82 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago
test_stress.py
Safe
1.5 kB
GLM-5.3 EXL3 3.38bpw on 4x DGX Spark: serving kit + incremental KV prefix cache
9 days ago