Add end-to-end MXFP4 Metal support
This commit is contained in:
@@ -12,7 +12,9 @@ use crate::model::{ModelChoice, validate_engine_artifacts};
|
||||
#[cfg(target_os = "macos")]
|
||||
use crate::settings::TurnSettings;
|
||||
use crate::settings::{EngineSettings, ReasoningMode};
|
||||
use gguf::{F16, F32, Gguf, I32, IQ2_XXS, Q2_K, Q4_0, Q4_K, Q5_K, Q6_K, Q8_0, Tensor, Value};
|
||||
use gguf::{
|
||||
F16, F32, Gguf, I32, IQ2_XXS, MXFP4, Q2_K, Q4_0, Q4_K, Q5_K, Q6_K, Q8_0, Tensor, Value,
|
||||
};
|
||||
#[cfg(target_os = "macos")]
|
||||
use kvstore::{KvStore, StoreReason};
|
||||
use sha2::{Digest, Sha256};
|
||||
@@ -53,7 +55,7 @@ pub(crate) use kvstore::sweep_unreachable as sweep_transient_cache;
|
||||
pub(crate) use metal::configure_sources as configure_metal_sources;
|
||||
|
||||
const DENSE: &[u32] = &[Q8_0, Q4_K, Q4_0];
|
||||
const ROUTED: &[u32] = &[Q8_0, IQ2_XXS, Q2_K, Q4_K, Q5_K, Q6_K];
|
||||
const ROUTED: &[u32] = &[Q8_0, IQ2_XXS, Q2_K, Q4_K, Q5_K, Q6_K, MXFP4];
|
||||
const PLAIN: &[u32] = &[F16, F32];
|
||||
const DSPARK_DENSE: &[u32] = &[F16, F32, Q8_0];
|
||||
|
||||
|
||||
Reference in New Issue
Block a user