11 Commits

Include renames

Author	SHA1	Message	Date
Salvatore Sanfilippo	29aa7267af	Extend ds4-eval with hard capability suite	2026-09-03 15:28:24 -07:00
antirez	a547fdff4a	Merge pull request #887 from kyuz0/perf/rocm-gfx1151-mmq-kernel-lab ... # Conflicts: # Makefile # ds4.c # ds4_bench.c # ds4_help.c # tests/test_gpu_args_cli.sh	2026-08-31 11:48:21 +02:00
Donato Capitella	17c2855987	Revert "bench: add untimed context baseline" ... This reverts commit e344bbef57b4713136ab703af392017ac80c7927.	2026-08-29 21:51:45 +01:00
Donato Capitella	985cacd07b	bench: add untimed context baseline	2026-08-29 21:51:45 +01:00
Donato Capitella	e73b367db9	feat(bench): add basic DSpark throughput support	2026-08-29 21:51:45 +01:00
antirez	ab993cb2a7	Accept ROCm backend in ds4-agent	2026-08-29 13:06:04 +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	abd4ed3885	cli: expose exact MTP sampling mode	2026-08-23 15:05:13 +02:00
antirez	8d683d6616	dspark: add opportunistic temperature sampling	2026-08-23 15:05:13 +02:00
antirez	66cbce5289	Unify distributed inference CLI and documentation	2026-07-18 18:50:24 +02:00
antirez	36ee8c1407	Add CUDA tensor parallelism and session batching	2026-07-18 18:50:03 +02:00