d28961d81e
* llama : enable chunked fused GDN path * models : avoid Q and K repeats when using fused GDA * cont : fix comment Co-authored-by: Aman Gupta <amangupta052@gmail.com> * cont : fix the fix Co-authored-by: Aman Gupta <amangupta052@gmail.com> * cont : fix * metal : add GDN kernel (#20361) * metal : add Metal backend for GGML_OP_GATED_DELTA_NET Add a fused Metal kernel for the gated delta net recurrence op (#19504), enabling GPU-accelerated inference for DeltaNet-based models (Qwen3.5, etc.) on Apple Silicon. Supports both GDA (scalar gate) and KDA (per-row gate) modes with head_size 64 and 128. Unsupported configurations (head_size 32, non-contiguous tensors) gracefully fall back to CPU. Performance: Qwen3.5-0.8B Q4_K_M on M4 Max tg128: 170 -> 213 t/s (+25%) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * metal : validate contiguity of all input tensors in supports_op Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * metal : add algorithm equivalence comment for GDA decay path Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * cont : unslop + optimize * cont : clean-up --------- Co-authored-by: Paul Flynn <paul@arkavo.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * CUDA: AR gated delta net improvements (#20391) * Add FastDiv to gated_delta_net_cuda * Shard columns across warps This reduces register pressure (avoids spill for S_v = 128) and gives the warp-scheduler more CTAs to schedule (thus hiding data-access latencies). * Remove unneded include in gated_delta_net.cu * Improve comments * Apply code-formating * Make sharding HIP-compatible 1. Use ggml_cuda_get_physical_warp_size() to determine warp size flexibly 2. Add test with partial warp to test sum reduction on CUDA * Remove fastdiv_s64, as we can treat neqk1 and rq3 as uint32_t * Rename variables * Enable GDN also for prefill, move TODO for chunked_GDN * Actually remove the TODO from 206890897546bd16602c3b79394fd5ea09ef199f * Get warp size at runtime warp_size is not known at compile time in hip host code. * Don't expose ggml_cuda_get_physical_warp_size on host --------- Co-authored-by: uvos <devnull@uvos.xyz> * llama : refactor llm_build_delta_net_base API --------- Co-authored-by: Aman Gupta <amangupta052@gmail.com> Co-authored-by: Paul Flynn <paul@arkavo.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Oliver Simons <osimons@nvidia.com> Co-authored-by: uvos <devnull@uvos.xyz>
47 lines
1.2 KiB
C++
47 lines
1.2 KiB
C++
#pragma once
|
|
|
|
#include "llama.h"
|
|
|
|
#include <cstdint>
|
|
|
|
#define LLAMA_MAX_SEQ 256
|
|
|
|
struct llama_cparams {
|
|
uint32_t n_ctx; // context size used during inference
|
|
uint32_t n_ctx_seq; // context for a single sequence
|
|
uint32_t n_batch;
|
|
uint32_t n_ubatch;
|
|
uint32_t n_seq_max;
|
|
int32_t n_threads; // number of threads to use for generation
|
|
int32_t n_threads_batch; // number of threads to use for batch processing
|
|
|
|
float rope_freq_base;
|
|
float rope_freq_scale;
|
|
|
|
uint32_t n_ctx_orig_yarn;
|
|
// These hyperparameters are not exposed in GGUF, because all
|
|
// existing YaRN models use the same values for them.
|
|
float yarn_ext_factor;
|
|
float yarn_attn_factor;
|
|
float yarn_beta_fast;
|
|
float yarn_beta_slow;
|
|
|
|
bool embeddings;
|
|
bool causal_attn;
|
|
bool offload_kqv;
|
|
bool flash_attn;
|
|
bool auto_fa;
|
|
bool fused_gdn_ar; // use fused gated delta net (autoregressive)
|
|
bool fused_gdn_ch; // use fused gated delta net (chunked)
|
|
bool auto_fgdn;
|
|
bool no_perf;
|
|
bool warmup;
|
|
bool op_offload;
|
|
bool kv_unified;
|
|
bool pipeline_parallel;
|
|
|
|
enum llama_pooling_type pooling_type;
|
|
|
|
ggml_backend_sched_eval_callback cb_eval;
|
|
void * cb_eval_user_data;
|
|
};
|