ROCm/HIP compatibility: managed memory fallback, FP8 path, UMA memory calc#6

Closed

JDL440 wants to merge 169 commits into

cchuter:masterfrom

JDL440:fix/rocm-fallback-managed-memory

Commits on May 5, 2026

Commits on May 6, 2026

Commits on May 7, 2026

Commits on May 8, 2026

Commits on May 9, 2026

Commits on May 10, 2026

Commits on May 11, 2026

Commits on May 12, 2026

metal : promote mul_mv/mul_mm batch divisors to function constants (#22711)
guyfischman
authored
convert : add split() to LoraTorchTensor in LoRA converter (#22832)

jesus-talavera-ibm
and
CISC
authored
mtmd: add MiMo v2.5 vision (#22883)
AesSedai
authored
ci : bump ty to 0.0.35 (#22961)
CISC
authored
vulkan: Check shared memory size for mmq shaders (#22693)
jeffbolznv
authored
vulkan: Fix Windows performance regression on Intel GPU BF16 workloads for Xe2 and newer (#22461)
rillomas
authored
examples : add llama-eval (#21152)

ggerganov
and
gatbontonpc
authored
model-conversion : add causal-convert-mmproj target [no ci] (#22969)
danbev
authored
ggml-webgpu: address precision issues for multimodal (#22808)
Constannnnnt
authored
ggml-webgpu: Enables running gpt-oss-20b (#22906)
yomaytk
authored
mtmd, server, common: expose modalities to /v1/models (#22952)
ngxson
authored
webui: Fix Chat Screen Form box disappearing + autoscroll issues on WebKit (#22977)
allozaur
authored
convert : fix Pixtral 12B --mistral-format conversion (3 bugs) (#22981)
fredzillman
authored
opencl: add opt-in Adreno xmem F16xF32 GEMM for prefill (#22755)

happyyzy
and
Your Name
authored

Commits on May 13, 2026

Commits on May 14, 2026

Commits on May 15, 2026

Commits on May 16, 2026

Commits on Jun 2, 2026

ROCm/HIP compatibility fixes: managed memory fallback, FP8 path, UMA memory calc
JDL440
committed