Donato Capitella a58d133c5e chore: update llama.cpp patch to PR 21566 for gemma-4 inference fix

2026-04-07 17:49:16 +01:00

..

ggml/src/ggml-cuda

moving folder to the right place

2025-11-12 11:12:07 +00:00

Dockerfile.rocm7-nightlies

chore: update llama.cpp patch to PR 21566 for gemma-4 inference fix

2026-04-07 17:49:16 +01:00

Dockerfile.rocm-6.4.4

patch: increasing MAX_REPETITION_THRESHOLD to allow complex agentic workflows

2026-03-25 09:23:19 +00:00

Dockerfile.rocm-7.2

patch: increasing MAX_REPETITION_THRESHOLD to allow complex agentic workflows

2026-03-25 09:23:19 +00:00

Dockerfile.vulkan-amdvlk

patch: increasing MAX_REPETITION_THRESHOLD to allow complex agentic workflows

2026-03-25 09:23:19 +00:00

Dockerfile.vulkan-radv

patch: increasing MAX_REPETITION_THRESHOLD to allow complex agentic workflows

2026-03-25 09:23:19 +00:00

gguf-vram-estimator.py

Updates to Dockerfile buil docs

2025-08-03 13:56:16 +01:00

hip-rocm7rc.patch

Updates to Dockerfile buil docs

2025-08-03 13:56:16 +01:00

llama-grammar.patch

fixed patch (AI slop!!!)

2026-03-25 09:36:50 +00:00