2a4cb50b52
chore: update benchmark execution script parameters and paths
2026-05-17 09:16:03 +01:00
2e3dc657d2
chore: update ROCm version to 7.2.3 and remove deprecated pr21344 toolbox
2026-05-11 19:40:30 +01:00
1bffd6505f
feat: add longctx65536 support to standard and RPC benchmark scripts
2026-05-01 20:19:02 +01:00
73be068e85
feat: upgrade ROCm toolboxes to 7.2.2 and update documentation and CI configurations
2026-04-26 16:25:44 +01:00
66a3314c22
refactor: update MODEL_DIR path to use absolute home directory reference
2026-04-15 11:39:35 +01:00
2c2c36d3da
add rocm-7.2.1-pr21344 toolbox (gfx1151 MMQ/MMVQ tile + nwarp tuning)
...
Adds a new toolbox variant based on PR #21344 (pedapudi/llama.cpp@gfx1151-opt)
which tunes MMQ tile sizes (x_max=48, y=64) and warp counts (nwarps=4) for
RDNA3_5 gfx1151, yielding up to +100% prefill throughput at small batch sizes.
Also adds BMI2/FMA/F16C CPU SIMD flags and GGML_CUDA_FA_ALL_QUANTS=ON to match
the benchmark build used in the PR. Wire up CI (build matrix + prune), the
refresh script, and run_benchmarks.sh so results land alongside rocm-7.2.1.
2026-04-15 09:23:58 +01:00
a821bcb91d
chore: update rocm-7.2 benchmark configuration to version 7.2.1
2026-04-10 11:48:27 +01:00
c129a04a1c
refactor: remove hblt0 benchmark support and associated comparison scripts
2026-04-10 11:23:06 +01:00
8ff812fbb5
updated benchmarks
2026-02-09 13:30:26 +00:00
06fc789eba
chore: deprecate and remove ROCm 7.1.1 toolbox and all associated references.
2026-02-04 17:56:41 +00:00
0635552fec
updated benchmark scripts
2026-01-23 08:55:25 +00:00
d6c7456bd0
adding system info to benchmark display
2026-01-11 10:04:05 +00:00
783998589e
neclean up of legacy toolboxes, removal of rocwmma and renamed rocm7-alpha to rocm-7nightlies. Added new benchmarks
2026-01-10 10:31:04 +00:00
9ba6812003
feat: upgrade ROCm to 7.1.1 and update associated tooling and documentation
2025-12-07 09:30:14 +00:00
ad32126872
Updating retries for run)_benchmark
2025-11-17 17:53:53 +00:00
12f057612b
restoring correct llama-bench flags
2025-11-17 16:00:10 +00:00
de02a53d96
restored correct benchmark behaviour
2025-11-17 15:55:31 +00:00
f62c6e47c5
updated benchmark script to cover HBLASLT for all rocm backends
2025-11-17 15:30:19 +00:00
1d945f2c21
change llama-bench retries to 3
2025-11-12 14:19:47 +00:00
79479ec596
adding rocm7alpha to the benchmarks
2025-11-12 14:06:00 +00:00
f93c88b792
limit llama-bench to 1 try to support longer context
2025-11-12 13:57:24 +00:00
11048c22f2
update benchmark script
2025-11-12 13:48:42 +00:00
ba88675b9c
Updated benchmarkls with ROCm 6.4.4
2025-09-28 09:38:04 +01:00
7dd4490398
updated benchmark script
2025-09-27 20:21:14 +01:00
b71a37647f
Updated benchmakrs, removed old toolboxes and results
2025-08-17 12:32:08 +01:00
62e5080102
Updated benchmarks
2025-08-17 08:53:16 +01:00
a9618d881b
- Corrected typo in WMMA (was spelt wrong as waam)
...
- Included rocm-7rc-rocwmma toolbox
- Included updated results from benchmarks including rocm 7rc with ROMWMMA and hipBLASLt
2025-08-10 13:21:06 +01:00
8972ef01ff
adding raw benchmark results
2025-08-09 10:44:09 +01:00
c534a1b1ee
Updated benchmark scirpt to skip combinations that have already been benchmarked
2025-08-06 18:16:30 +01:00
e7e27e6cf3
Benchmark and container updates
2025-08-03 13:05:52 +01:00
Donato Capitella