Niko1221 39cd7fbef4 setup: the CUDA 12 engine's driver floor per OS (Windows 527.41 -> 528, Linux 525); the wheel pins match the 12.9.1 toolkit

2026-10-04 08:01:18 +02:00

..

benchmarks

AMD HIP backend for gfx1100 (PR #121, squashed onto its 0.1.21 base)

2026-09-29 14:33:45 +02:00

media

README: How does it work? in plain words, with illustrations in the app's style (colors, icons, font; light and dark)

2026-09-28 14:38:40 +02:00

paper

Strata: Qwen3.8-Flash-Next on a 12-24 GB NVIDIA GPU + 64 GB RAM, one-click install

2026-09-24 18:42:20 +02:00

AI_SETUP.md

docs: Older GPUs (experimental) - the support matrix, the CUDA 12 engine and how to opt in

2026-10-03 23:44:14 +02:00

AMD_HIP_PERFORMANCE.md

Low-RAM mode, resident variant: the experts the GPU does not hold stay in RAM (--resident-experts), chosen by setup

2026-09-30 16:51:04 +02:00

AMD_HIP.md

docs: Older GPUs (experimental) - the support matrix, the CUDA 12 engine and how to opt in

2026-10-03 23:44:14 +02:00

COMMUNITY_BENCHMARKS.md

bench: community report, 2x AMD Instinct MI50 (gfx906), Coder IQ1_M, 4K to 128K prompt tokens

2026-10-03 23:33:55 +02:00

DETAILS.md

Merge branch 'f-139-big' into f-139-rel

2026-10-03 20:05:05 +02:00

HOW_IT_WORKS.md

docs: a short README for regular people; the details move to INSTALL, MODELS, TROUBLESHOOTING, HOW_IT_WORKS

2026-10-01 20:08:58 +02:00

INSTALL.md

Merge branch 'f-139-ux' into f-139-rel

2026-10-03 20:03:53 +02:00

MCP_SERVER.md

tools/strata_mcp.py: an MCP server so an AI assistant can install, start, check and stop Strata (#133)

2026-10-01 20:18:07 +02:00

MODELS.md

setup: Unsloth's UD-IQ4_XS as an experimental choice (#621)

2026-10-03 18:36:44 +02:00

MULTI_GPU.md

layer split trim: opt-in on HIP too (STRATA_STAGE_TRIM=1, PR #639)

2026-10-03 20:05:31 +02:00

NVIDIA_V100.md

docs: Older GPUs (experimental) - the support matrix, the CUDA 12 engine and how to opt in

2026-10-03 23:44:14 +02:00

OLDER_GPUS.md

setup: the CUDA 12 engine's driver floor per OS (Windows 527.41 -> 528, Linux 525); the wheel pins match the 12.9.1 toolkit

2026-10-04 08:01:18 +02:00

ORCA_Q4_K_S.md

#296 follow-up: only the Q5_0 MMQ instance and case stay (Q4_K / Q5_1 come with S5's STRATA_MMQ_KQUANTS)

2026-10-01 10:31:23 +02:00

ORCA.md

Support Orca IQ3_XXS with explicit BF16 compatibility packing

2026-09-27 14:10:52 -06:00

SECOND_GPU.md

docs: the refused --peer-device combinations

2026-10-02 22:04:42 +02:00

TROUBLESHOOTING.md

setup: STRATA_NVCC picks the CUDA toolkit; CUDA_HOME is looked at; glibc 2.43 + CUDA 12.9 and gcc 15 documented (#601)

2026-10-03 18:25:30 +02:00

UNSLOTH_Q4.md

setup: Unsloth's UD-IQ4_XS as an experimental choice (#621)

2026-10-03 18:36:44 +02:00