ivanfioravanti bcd1e57c5e metal: exact MXFP4 speedups for rounds 7-9 ...

Integrate the MXFP4 Metal decode/prefill optimizations (rounds 7-9) as one
commit. Keep both the MXFP4 half_lut/tail_cull down-pipeline selection and
main's mpp_mask override for IQ2_XXS gate/up and Q2_K/IQ2_XXS down; they
target disjoint quant types and coexist.

2026-08-09 11:38:00 +02:00

..

test-vectors

Version DeepSeek Flash fixtures by checkpoint

2026-08-03 19:25:05 +02:00

cuda_long_context_smoke.c

cuda: warm up top-k regression timing

2026-06-02 09:07:28 +02:00

ds4_agent_test.c

Add ds4-agent edit regression tests

2026-06-10 00:08:36 +02:00

ds4_test.c

metal: exact MXFP4 speedups for rounds 7-9

2026-08-09 11:38:00 +02:00

dspark_acceptance_fixture.sh

Update Flash downloads and DSpark support for 0731

2026-08-04 13:00:44 +02:00

generate_long_context_story_prompt.py

Add long-context story recall regression

2026-05-13 19:11:16 +02:00

glm_long_context_smoke.sh

Unify distributed inference CLI and documentation

2026-07-18 18:50:24 +02:00

long_context_security_prompt.txt

DS4 initial release

2026-05-07 17:16:28 +02:00

long_context_story_prompt.txt

Add long-context story recall regression

2026-05-13 19:11:16 +02:00

test_cuda_mixed_batch.c

Unify distributed inference CLI and documentation

2026-07-18 18:50:24 +02:00

test_cuda_session_batch.c

Make batched server prefill quantum configurable

2026-08-03 10:07:30 +02:00

test_engine_correctness.c

Add CUDA tensor parallelism and session batching

2026-07-18 18:50:03 +02:00

test_engine_mgpu_placement.c

Account for batched GLM session memory during placement

2026-08-03 14:48:05 +02:00

test_engine_mgpu_refusal.c

Make release builds warning-free

2026-07-20 11:09:28 +02:00

test_engine_mgpu_runtime.c

Add CUDA tensor parallelism and session batching

2026-07-18 18:50:03 +02:00

test_gpu_args_cli.sh

Unify distributed inference CLI and documentation

2026-07-18 18:50:24 +02:00

test_gpu_args.c

Add CUDA tensor parallelism and session batching

2026-07-18 18:50:03 +02:00

test_gpu_lookup_cache_strict.c

Add CUDA tensor parallelism and session batching

2026-07-18 18:50:03 +02:00

test_gpu_model_cache.c

Add CUDA tensor parallelism and session batching

2026-07-18 18:50:03 +02:00

test_gpu_xdev.c

Add CUDA tensor parallelism and session batching

2026-07-18 18:50:03 +02:00

test_layer_pack.c

Add CUDA tensor parallelism and session batching

2026-07-18 18:50:03 +02:00

test_metal_session_batch.c

Stabilize CUDA and Metal session batching

2026-07-18 18:50:59 +02:00

test_mxfp4_cuda.cu

Add native MXFP4 inference to CUDA

2026-08-03 13:13:50 +02:00

test_mxfp4_dot.c

Add MXFP4 GGUF format and scalar reference

2026-08-01 09:50:29 +02:00

test_mxfp4_metal.c

metal: exact MXFP4 speedups for rounds 7-9

2026-08-09 11:38:00 +02:00

test_q4k_dot.c

Keep Q4K regression test warning-free

2026-08-04 13:57:21 +02:00

test_sampling.c

metal: exact MXFP4 speedups for rounds 7-9

2026-08-09 11:38:00 +02:00

test_server_batching.py

Make batched server prefill quantum configurable

2026-08-03 10:07:30 +02:00