8 Commits

Include renames

Author	SHA1	Message	Date
antirez	467b6f05a0	Harden Qwen Metal batch integration and quality checks	2026-09-16 14:14:36 +02:00
Salvatore Sanfilippo	bd66c40207	DeepSeek v4.1 Flash support for Metal	2026-09-12 11:47:54 +02:00
antirez	87495f6cc9	Add live steering controls	2026-08-30 13:33:09 +02:00
Salvatore Sanfilippo	8adb22178c	Add GLM 5.3 directional steering	2026-08-29 22:31:32 +02:00
antirez	147109a3cc	Add GLM 5.3 Flash inference ... Implement GLM 5.3 Q2 and Q4 inference across Metal and CUDA, including tensor parallelism, RDMA, batching, MTP, snapshots, SSD streaming, and GLM 5.2 shared-path improvements. Add quantization and validation tools, official quality fixtures, model downloads, regression coverage, release QA, and user documentation.	2026-08-28 23:26:29 +02:00
antirez	a185c36dc4	Stabilize CUDA and Metal session batching	2026-07-18 18:50:59 +02:00
antirez	36ee8c1407	Add CUDA tensor parallelism and session batching	2026-07-18 18:50:03 +02:00
antirez	36cd0ca915	Add native Metal session batching	2026-07-18 18:49:00 +02:00