Popular repositories Loading
-
qwen38-27b-rtx3090
qwen38-27b-rtx3090 PublicQwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-ou…
-
-
agentic-coding-playbook
agentic-coding-playbook PublicSyv.ai's agentic coding playbook
Repositories
Showing 10 of 19 repositories
- qwen38-27b-rtx3090 Public
Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks
- plapre Public
- dash Public
- trivsel Public
- slimdeploy Public
- it-center-fyn Public
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…