metal

Tag

Cards List
#metal

@no_stp_on_snek: vllm-swift 0.6.3 + longctx 0.3.2 are out. highlights: - triattentionv3 + longctx rescue path hits 256k niah on apple si…

X AI KOLs Following · 6h ago Cached

vllm-swift 0.6.3 and longctx 0.3.2 releases bring triattentionv3 with 256k context on Apple Silicon, Gemma 4 MTP drafter support, Hermes tool calling with auto-recovery, and a longctx-svc daemon for scaling to 12M-token corpora.

0 favorites 0 likes
#metal

@VincentLogic: Discovered an amazing open-source project! Redis creator antirez made a splash! ds4 — DeepSeek V4 Flash local inference engine, optimized for Mac Metal, topping GitHub charts for days! And here's the killer part: 128GB…

X AI KOLs Timeline · 19h ago

Redis creator antirez released an open-source project called ds4, a DeepSeek V4 Flash local inference engine optimized for Mac Metal, featuring disk KV caching, ultra-long context, and excellent performance.

0 favorites 0 likes
#metal

@antirez: Announcing with gratitude that @audreyt just gifted me an M5 Max 128GB MacBook Pro! It will let me develop DwarfStar4 (…

X AI KOLs Timeline · yesterday

antirez announces receiving an M5 Max 128GB MacBook Pro from audreyt to develop DwarfStar4 and experiment with distributed inference across M3 Max and M5 Max hardware.

0 favorites 0 likes
#metal

@antirez: I just pushed a big refactoring of DS4 backends with CUDA support and single direction activation steering. The Metal p…

X AI KOLs Timeline · 3d ago

antirez pushed a major refactoring of DS4 backends, adding CUDA support and single direction activation steering while preserving the Metal path. Only M3 and DGX Spark hardware are supported for now.

0 favorites 0 likes
#metal

DeepSeek 4 Flash local inference engine for Metal

Hacker News Top · 6d ago Cached

ds4 is a native local inference engine for DeepSeek V4 Flash optimized for Apple Silicon, featuring disk-based KV cache persistence and Metal acceleration.

0 favorites 0 likes
← Back to home

Submit Feedback