0
Fork 0
mirror of https://github.com/zml/zml.git synced 2026-11-16 19:11:09 +00:00
zml/examples/llm/models
Hugo Mano 1042cba3ff
zml/kernels/moe: make mesh and partitioning explicit (#1028)
MOE API currently relies on input sharding metadata or
partitioning choices made inside backend kernels. Ordinary graph
operations can leave that metadata unspecified, making the resulting
sharding depend on the backend and preceding operations.

Move the manual computation boundary into the shared
`zml.kernels.moe.forwardMoe` API using `manualComputation2`. 
Callers provide a logical mesh and typed input/output partitioning specs.
History 2026-11-09 15:26:03 +01:00
..
lfm2 zml/attention: declare manual partitioning in the shared API instead of kernels (#1016) 2026-11-05 13:00:00 +01:00
llama zml/attention: declare manual partitioning in the shared API instead of kernels (#1016) 2026-11-05 13:00:00 +01:00
qwen3_5 zml/attention: declare manual partitioning in the shared API instead of kernels (#1016) 2026-11-05 13:00:00 +01:00
qwen3_5_moe zml/kernels/moe: make mesh and partitioning explicit (#1028) 2026-11-09 15:26:03 +01:00
common.zig zml/platform: Add furiosa platform (#871) 2026-10-09 12:21:16 +02:00
lfm2.zig examples/llm: Simplifications (#430) 2026-03-24 18:16:25 +01:00
lfm2_tests.zig zml: re-structure attention kernels (#926) 2026-10-12 20:31:17 +02:00
llama.zig examples/llm: Simplifications (#430) 2026-03-24 18:16:25 +01:00
llama_tests.zig zml/Tensor: explicit sharding in Tensor code (#868) 2026-10-06 15:37:22 +02:00
qwen3_5.zig examples/llm: Simplifications (#430) 2026-03-24 18:16:25 +01:00
qwen3_5_moe.zig zml/moe : Moe backend triton zig, qwen3_5_moe model (#529) 2026-05-15 11:06:02 +02:00