AI Coding Live News — Real-Time 𝕏/Twitter Updates & Breakthroughs

LightSeek Foundation@lightseekorg·Collected 64d ago

👀56

🔥90

LightSeek open-sources Kimi K3 draft trio: EAGLE-3, DFlash2, DSpark via TorchSpec + vLLM

LightSeek Foundation released a Kimi K3 draft-model collection (EAGLE-3, DFlash2, DSpark) trained with TorchSpec on 40 NVIDIA GB200 GPUs, with open data recipes. Their blog reports acceptance length across 10 benchmarks and SPEED-Bench end-to-end throughput; DFlash2 averages ~4.02 accepted tokens and leads EAGLE-3 at lower concurrency.

Key Takeaways

Three draft architectures for Kimi K3 speculative decoding: EAGLE-3, DFlash2, DSpark.
Trained on 40×GB200 with TorchSpec; data recipes plus Docker/CI shared.
On HumanEval, DFlash2 acceptance length ~5.08 vs EAGLE-3 ~3.29.

Read full story

Linked Models & Agents:

#Kimi K3#LightSeek#TorchSpec#vLLM#EAGLE-3#DFlash2#DSpark#speculative decoding#GB200

vLLM@vllm_project·Collected 68d ago

👀56

🔥95

View on 𝕏 ↗

vLLM 0.28.0 Released: Full-Stack Kimi-K3, DeepSeek-V4 Sparse MLA, and Tiered Disk KV Cache

vLLM 0.28.0 landed with 584 commits, bringing stack-wide Kimi-K3 support, end-to-end DeepSeek-V4 sparse MLA with DFlash2/DSpark speculative decoding, Model Runner V2 disaggregation, and tiered disk KV cache.

Key Takeaways

Adaptive speculative token budgets slash end-to-end TTFT by 55–65% with 1.5–3x faster sequence-parallel kernels;
End-to-end DeepSeek-V4 sparse MLA and Kimi-K3 shared-expert sharding save ~17 GiB VRAM per GPU;
Tiered KV cache introduces a disk tier, doubles max batched tokens to 16,384, and supports diverse hardware backends.

Read full story

Linked Models & Agents:

⚡ DeepSeek-V4-Flash ⚡ DeepSeek-V3