b9904
[SYCL] fix unsupported UT cases of CONT & CPY (#25231) fix unsupported UT cases of CONT & CPY update ops.md rm unused head file macOS/iOS: macOS…
Latest
b9902
[SYCL] support OP cross_entropy_loss, cross_entropy_loss_back (#25236) support OP cross_entropy_loss, cross_entropy_loss_back correct format issue macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…
b9901
sycl : set K_QUANTS_PER_ITERATION to 1 on DMMV path (#25063) sycl: add supported types to ggml_sycl_supports_reorder_dmmv The reordered feature is implemented in ggml_sycl_op_dequantize_mul_mat_vec, but gated by…
b9899
sycl : enhance argsort to support all UT cases (#25125) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…
b9898
sycl : use sycl func to fix AOT double type issue (#25081) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel…
b9897
sycl : rename the env vars from "disable" to "enable" (#25042) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
b9895
speculative : fix out-of-bounds read in ngram-map on prompt shrink (#23936) speculative : fix out-of-bounds read in ngram-map on prompt shrink speculative : fix ngram-map cleanup…
b9894
vulkan : check src0 type in GGML_OP_SET_ROWS to avoid failures due to unimplemented f16 support (#25351) vulkan : check src0 type in GGML_OP_SET_ROWS to avoid failures…
b9893
opencl: general flash attention decode performance optimizations (#25366) opencl: vec flash-attention decode kernels for f16/q8_0/q4_0 KV opencl: improve non FA KQ mv kernels opencl: tweaks for…
b9892
common: Set optimal default thread count for ppc ( linux as well as AIX) (#25237) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled)…