thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

llama : enable chunked fused GDN path (#20340)

Browse source 
* 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>
This commit is contained in:
Georgi Gerganov 2026-03-11 22:46:40 +02:00 • committed by GitHub
parent f90bd1dd84
commit d28961d81e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 674 additions and 165 deletions
Download patch file Download diff file Expand all files Collapse all files

5
tests/test-backend-ops.cpp
View file

@ -8447,6 +8447,9 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
}
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 32, 128, 1, 1));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 32, 16, 1, 1));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 32, 16, 1, 1, 1, true, true));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 32, 16, 1, 1, 1, false, true));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 16, 64, 1, 2));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 4, 64, 4, 1));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 4, 64, 4, 2));
@ -8456,10 +8459,12 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
// KDA (vector gate)
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 4, 64, 1, 1, 1, false, true));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 4, 64, 1, 2, 1, false, true));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 4, 16, 1, 2, 1, false, true));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 4, 32, 4, 1, 1, false, true));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 4, 64, 4, 2, 1, false, true));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 8, 32, 4, 2, 2, false, true));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 4, 64, 4, 2, 1, true, true));
test_cases.emplace_back(new test_gated_delta_net(GGML_TYPE_F32, 4, 16, 4, 2, 1, true, true));
#if 0
// these tests are disabled to save execution time, sbut they can be handy for debugging