el-engine-candle 0.3.6

RuntimeAcl: InferenceEngine over Candle — real CPU forward (ADR-002).

Coverage
100%
12 out of 12 items documented0 out of 11 items with examples
Size
Source code size: 86.28 kB This is the summed size of all the files inside the crates.io package for this release.
Documentation size: 1.21 MB This is the summed size of all files generated by rustdoc for all configured targets
Ø build duration
this release: 35s Average build duration of successful builds.
all releases: 39s Average build duration of successful builds in releases after 2024-10-23.
Links
crates.io
Dependencies
Versions
Owners

el-engine-candle — inference engine adapter over Candle (ADR-002), implementing [el_runtime::InferenceEngine] / RuntimeAcl.

Consumers supply their own model file; see [CandleEngine::from_path] and [CandleEngine::from_bytes]. For tests that need a working engine without a model asset, use [CandleEngine::toy].

Expected GGUF tensor names:

token_embd.weight — embedding table [vocab, dim]
output.weight or lm_head.weight — lm-head [vocab, dim] (standard Llama layout)

Float logits are quantised to integer milli-logits at the ACL boundary, so Candle's Tensor/Device types never cross into the domain.