GPU is starving – LLM host dispatch at 191k steps/s on 1 vCPU
Run Autonomous Verification & Anti-Cheat Suite ./scripts/run_audit.sh Executes the standalone, zero-dependency binary bin/floria-serving-audit (489 KB). Verifies 7/7 formal invariants in < 2s: FP64 ground truth concordance, zero GPU starvation over 1 200 requests, 100% recycled KV blocks (16 384 / 16 384 blocks), and sub-microsecond dispatch. Interactive Local Benchmark # Standard benchmark (batch 64, prompt 64, 180 steps) ./scripts/run_bench.sh 64 64 180 # Multi-core NUMA sharded benchmark ./scripts/run_bench.sh --sharded --shards-range 1,2,4,8,16 -c 256,512,1024,2048,4096 3.
- ▪Run Autonomous Verification & Anti-Cheat Suite ./scripts/run_audit.sh Executes the standalone, zero-dependency binary bin/floria-serving-audit (489 KB).
- ▪Verifies 7/7 formal invariants in < 2s: FP64 ground truth concordance, zero GPU starvation over 1 200 requests, 100% recycled KV blocks (16 384 / 16 384 blocks), and sub-microsecond dispatch.
- ▪Interactive Local Benchmark # Standard benchmark (batch 64, prompt 64, 180 steps) ./scripts/run_bench.sh 64 64 180 # Multi-core NUMA sharded benchmark ./scripts/run_bench.sh --sharded --shards-range 1,2,4,8,16 -c 256,512,1024,2048,4096 3.
Hacker News (AI / LLM) files mainly under ai. We currently carry 5,977 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/cortexLab011/floria-serving |
| Publication time | Tue, 22 Sep 2026 13:04:13 +0000 |
| Retrieval time | 2026-09-22T13:13:51.615Z |
| Last seen | 2026-09-22T13:13:51.615Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | UeS51jf4Xg41 · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
FLORIA-SERVING (COMMUNITY LAUNCH PACK) Native High-Throughput Serving & Continuous Batching Acceleration Engine for Dense LLMs Publisher & Authors: The Floria Authors | Floria Systems Research Proven Physical Records (In-Situ Validated) Breakthrough Metric Hardware Node & Implementation Measured Score Industrial Impact Host Scheduler Multi-Streaming Intel Xeon 8470 (32 Shards) + NVIDIA H100 5 617 953.3 tok/s (8 192 streams) Host scheduler saturation (Jitter: 1.04) Hopper TMA Attention Kernel NVIDIA H100 SXM5 (Triton TMA/WGMMA) 1.25 ms (879.6 TFLOPS) +48.0% throughput vs PyTorch SDPA (1.48x) 1-vCPU Host Saturation Intel Xeon Platinum (AVX-512 Native) 191 617.3 tok/s (1 vCPU core) +2 041.0% throughput vs vLLM v0.6.0 Hardware Step Arbitration AMD EPYC 75F3 (Native Scheduler) 8.505 us / step…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.