beam
beam
Discover
PulseActivityAnalyticsBest forMapOrgs
Niches
AgentsMCPRAGCoding AssistantsInference & ServingVector DBs
Personal
WatchlistCompareWeekly report
?
Sign in
magic link · no password
LIVE──────── · ──:──:── UTCabout
beam
beam
Discover
PulseActivityAnalyticsBest forMapOrgs
Niches
AgentsMCPRAGCoding AssistantsInference & ServingVector DBs
Personal
WatchlistCompareWeekly report
?
Sign in
magic link · no password
Back to Pulse
Tool profile

raullenchai/twinspark

stable
Single maintainer

Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster, reboot-verified, tuned DSpark speculative decoding (~75 tok/s), full benchmarks, OpenAI Codex CLI integration

deepseekdgx-sparkllm-inferencelocal-llmvllm
Velocity score
0.02/ 10
[STARS]
178
[FORKS]
20
[CONTRIBUTORS]
1
[LAST_COMMIT]
1mo ago
OPEN_ON_GITHUB
Velocity class: stable
Is raullenchai/twinspark still actively maintained?
[VR]

This tool is in the Velocity Report when it moves. Get the weekly numbers.

Score breakdown
461/ 1000
inference · raullenchai/twinspark
Velocity50%
Adoption30%
Maintenance15%
Community5%
[CODE_GROWTH]
493
[INSTALL_VEL]
498
[ACTIVITY]
373
[COMMUNITY_SIGNAL]
176

Terminal score: 0–1000 raw, weighted across 4 dimensions. Public score: 0–10 normalized (shown in the 30-day stars chart above).

LIVE──────── · ──:──:── UTCabout