This website requires JavaScript.
About
Status
₊˚⊹Discord
Explore
Register
Sign in
Reference in a new issue
Blame
Copy permalink
Reference in a new issue
Copy permalink
DKB
/
zml
Star
0
Fork
You've already forked zml
0
mirror of
https://github.com/zml/zml.git
synced
2026-11-16 19:11:09 +00:00
Code
Issues
23
Releases
1
Packages
Activity
raphael/decoder-buffer
zml
/
platforms
/
neuron
/
python_launcher.zig
155 lines
5.5 KiB
Raw
Permalink
Normal View
History
platforms/neuron: introduce NKI stack with SDPA kernel (#528) **Summary** This PR update to Neuron v2.30, introduces the Neuron NKI stack into ZML and wires it into the LLM attention path. The main goal is to make Neuron attention run through NKI kernels. It adds the compiler/runtime plumbing needed to embed NKI kernels as Neuron custom-native calls, then uses that path for SDPA-style prefill/decode attention. Paged Attention will come later. On inf2.8xlarge it runs : - 25 tok/s for Llama 3.1 8B BF16 - 63.5 tok/s for LFM2.5-1.2B-Instruct BF16 - 19 tok/s for Qwen3.5-9B BF16
2026-06-16 10:57:00 +02:00
zig 0.17 (second attempt) (#923) Bump for zig 0.17 Deps: - uucode bumped to https://github.com/jacobsandlund/uucode/commit/1fb73433bba5d93366c57f23ff2e9d7939746500 - zigimg bumped to https://github.com/zigimg/zigimg/commit/734fa919fb15b7917d4eb124f53600348f4ffa30 - libvaxis bumped to https://github.com/rockorager/libvaxis/commit/14b7684272234a3d66316c0d1bbdc876d4e8997c - zio bumped to: https://github.com/lalinsky/zio/commit/417757935ef6d0f0a2396d4023a44ca82ac1901c - rules_zig upgraded to [version 0.17](https://github.com/hermeticbuild/rules_zig/releases/tag/v0.17.0) - zls is using a commit from master, but they don't have yet a tagged release so Codex did a bit of packaging. I confirmed it correctly autocompletes on my machine
2026-10-13 17:11:38 +02:00
platforms/neuron: introduce NKI stack with SDPA kernel (#528) **Summary** This PR update to Neuron v2.30, introduces the Neuron NKI stack into ZML and wires it into the LLM attention path. The main goal is to make Neuron attention run through NKI kernels. It adds the compiler/runtime plumbing needed to embed NKI kernels as Neuron custom-native calls, then uses that path for SDPA-style prefill/decode attention. Paged Attention will come later. On inf2.8xlarge it runs : - 25 tok/s for Llama 3.1 8B BF16 - 63.5 tok/s for LFM2.5-1.2B-Instruct BF16 - 19 tok/s for Qwen3.5-9B BF16
2026-06-16 10:57:00 +02:00
zig 0.17 (second attempt) (#923) Bump for zig 0.17 Deps: - uucode bumped to https://github.com/jacobsandlund/uucode/commit/1fb73433bba5d93366c57f23ff2e9d7939746500 - zigimg bumped to https://github.com/zigimg/zigimg/commit/734fa919fb15b7917d4eb124f53600348f4ffa30 - libvaxis bumped to https://github.com/rockorager/libvaxis/commit/14b7684272234a3d66316c0d1bbdc876d4e8997c - zio bumped to: https://github.com/lalinsky/zio/commit/417757935ef6d0f0a2396d4023a44ca82ac1901c - rules_zig upgraded to [version 0.17](https://github.com/hermeticbuild/rules_zig/releases/tag/v0.17.0) - zls is using a commit from master, but they don't have yet a tagged release so Codex did a bit of packaging. I confirmed it correctly autocompletes on my machine
2026-10-13 17:11:38 +02:00
platforms/neuron: introduce NKI stack with SDPA kernel (#528) **Summary** This PR update to Neuron v2.30, introduces the Neuron NKI stack into ZML and wires it into the LLM attention path. The main goal is to make Neuron attention run through NKI kernels. It adds the compiler/runtime plumbing needed to embed NKI kernels as Neuron custom-native calls, then uses that path for SDPA-style prefill/decode attention. Paged Attention will come later. On inf2.8xlarge it runs : - 25 tok/s for Llama 3.1 8B BF16 - 63.5 tok/s for LFM2.5-1.2B-Instruct BF16 - 19 tok/s for Qwen3.5-9B BF16
2026-06-16 10:57:00 +02:00
zig 0.17 (second attempt) (#923) Bump for zig 0.17 Deps: - uucode bumped to https://github.com/jacobsandlund/uucode/commit/1fb73433bba5d93366c57f23ff2e9d7939746500 - zigimg bumped to https://github.com/zigimg/zigimg/commit/734fa919fb15b7917d4eb124f53600348f4ffa30 - libvaxis bumped to https://github.com/rockorager/libvaxis/commit/14b7684272234a3d66316c0d1bbdc876d4e8997c - zio bumped to: https://github.com/lalinsky/zio/commit/417757935ef6d0f0a2396d4023a44ca82ac1901c - rules_zig upgraded to [version 0.17](https://github.com/hermeticbuild/rules_zig/releases/tag/v0.17.0) - zls is using a commit from master, but they don't have yet a tagged release so Codex did a bit of packaging. I confirmed it correctly autocompletes on my machine
2026-10-13 17:11:38 +02:00
platforms/neuron: introduce NKI stack with SDPA kernel (#528) **Summary** This PR update to Neuron v2.30, introduces the Neuron NKI stack into ZML and wires it into the LLM attention path. The main goal is to make Neuron attention run through NKI kernels. It adds the compiler/runtime plumbing needed to embed NKI kernels as Neuron custom-native calls, then uses that path for SDPA-style prefill/decode attention. Paged Attention will come later. On inf2.8xlarge it runs : - 25 tok/s for Llama 3.1 8B BF16 - 63.5 tok/s for LFM2.5-1.2B-Instruct BF16 - 19 tok/s for Qwen3.5-9B BF16
2026-06-16 10:57:00 +02:00