ProprietaryLegal / Volta-sPLIt-DeepSeek-V4.1-Flash-1017-8xV100-SXM2-PP2xTP4
DeepSeek-V4.1-Flash-1017 on 8x V100-SXM2 (2018): 119.0 tok/s decode, 120.8 thinking on (measured), 524K context, 300K-token first token in 178 s. PP2xTP4 port of 1Cat-vLLM #1277 with every patch, measurement and lost lever. PLI Labs.
Why this job: topics: llm-inference, gguf, vllm
What it does
Decode speed depends on what the model is writing, much less on how long the prompt is. MEASURED 2026-11-05 on the checkpoint build, one request at a time, thinking off, greedy, 1,024 tokens out:
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 4 days ago
- Stars
- 17
- +16 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 55% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 0% closed
- 1 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| incoai / splash | 2,170 | 4 days ago | Apache-2.0 | Mac |
| syv-ai / HyperQwen | 2,639 | today | Apache-2.0 | No downloads |
| mw00 / project-maya | 2,741 | yesterday | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 55%
- Shell 38%
- Cuda 7%
Topics
- cuda
- deepseek
- gguf
- llm-inference
- speculative-decoding
- v100
- vllm
- volta
Project record
- JobLocal LLMs
- StatusNew to our list
- Commits10
- Forks2
- Watching1
- CreatedNov 3, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026