 Lizonghang
|
a46d56cc60
|
llama_model_n_flops: remove ctxs
|
2024-12-06 11:31:53 +04:00 |
|
|
Lizonghang
|
f1c1d1b929
|
add support for Q5_K and fix byte count for Q6_K
|
2024-12-06 07:59:45 +04:00 |
|
|
Lizonghang
|
e6f4c009ab
|
device_disk_access_delay: add delay for loading one row from lookup table
|
2024-12-05 20:38:28 +04:00 |
|
|
Lizonghang
|
4fd3b6679e
|
fix n_gpu_layers
|
2024-12-05 20:28:19 +04:00 |
|
|
Lizonghang
|
3c8dbd11fc
|
device_compute_delay: compatible with the shared memory in Metal
|
2024-12-05 20:02:13 +04:00 |
|
|
Lizonghang
|
e74967c488
|
throw error when using async upload, will support later
|
2024-12-05 14:18:39 +04:00 |
|
|
Zonghang Li
|
5a99c5894d
|
update test model, enable warm-up and sched
|
2024-12-05 09:52:16 +04:00 |
|
|
Lizonghang
|
b9538f048a
|
add sched in device_flops but disabled by default
|
2024-12-04 23:54:57 +04:00 |
|
|
Zonghang Li
|
7521e532c4
|
device_memory_bw: simulate cache-friendly block access and multi-threading
|
2024-12-04 15:36:59 +04:00 |
|
|
Zonghang Li
|
44b4718c8b
|
recover device_memory_access_delay
|
2024-12-04 12:29:24 +04:00 |
|
|
Zonghang Li
|
89aad7880e
|
fix sysctlbyname on Linux and Win
|
2024-12-04 12:24:07 +04:00 |
|
|
Lizonghang
|
585864b05a
|
add inactive_memory in Mac UMA
|
2024-12-04 11:56:09 +04:00 |
|
|
Lizonghang
|
99d48157a0
|
compatible with Mac ARM64 and x86_64 arch, and ignore memory access delay
|
2024-12-04 11:33:46 +04:00 |
|
|
Zonghang Li
|
6d7801de87
|
fix available_memory calculation
|
2024-12-04 10:36:43 +04:00 |
|
|
Lizonghang
|
75a86e4eb1
|
use internal_mem - purgeable_mem to calculate the available_mem
|
2024-12-04 10:24:54 +04:00 |
|
|
Lizonghang
|
bd5e034746
|
set fio engine to sync if posixaio not loadable
|
2024-12-04 00:55:50 +04:00 |
|
|
Lizonghang
|
508c8ae83c
|
set fio engine to sync if posixaio not loadable
|
2024-12-04 00:52:01 +04:00 |
|
|
Lizonghang
|
c3d708862c
|
use disk read_rnd_bw by default
|
2024-12-04 00:37:59 +04:00 |
|
|
Lizonghang
|
7cd4936d58
|
rename to CPU RAM Read BW
|
2024-12-04 00:04:22 +04:00 |
|
|
Lizonghang
|
dc03b6216f
|
set default page size to 4KB if not available from system
|
2024-12-03 23:25:47 +04:00 |
|
|
Lizonghang
|
74dbec5086
|
set default readahead size to 128KB if permission is needed
|
2024-12-03 22:55:16 +04:00 |
|
|
Zonghang Li
|
1a7237636e
|
add cgroup version detect
|
2024-11-30 09:48:19 +04:00 |
|
|
Zonghang Li
|
3074763ed4
|
fix memory detect in docker container
|
2024-11-30 09:36:01 +04:00 |
|
|
Zonghang Li
|
eb25858e87
|
remove cpus_allowed_policy in fio
|
2024-11-29 22:16:32 +04:00 |
|
|
Zonghang Li
|
7e4bb65eab
|
fix bugs on cpu
|
2024-11-29 22:06:02 +04:00 |
|
|
Zonghang Li
|
81fd77033e
|
add gpu support in device_memory_access_delay
|
2024-11-29 21:56:01 +04:00 |
|
|
Lizonghang
|
6f54a12c7d
|
add gpu support in llama_model_kvcache_size and llama_model_compute_buf_size
|
2024-11-29 21:06:32 +04:00 |
|
|
Lizonghang
|
f8e9dc2713
|
add GPU support in device_compute_delay and device_disk_access_delay
|
2024-11-29 20:21:22 +04:00 |
|
|
Lizonghang
|
f8bcf38bfe
|
fix var name overwrite
|
2024-11-29 20:00:17 +04:00 |
|
|
Lizonghang
|
1123c00e45
|
recover comments in llama_profile_device
|
2024-11-29 19:07:07 +04:00 |
|
|
Lizonghang
|
68ecabc8c3
|
add cpu_read_ram_bw, metal_read_vram_bw, cuda_read_vram_bw
|
2024-11-29 19:04:53 +04:00 |
|
|
Lizonghang
|
0a6ffe68e0
|
add kernel kernel_read_vram
|
2024-11-29 17:15:36 +04:00 |
|
|
Lizonghang
|
639a33dfa5
|
add op GGML_OP_READ and GGML_METAL_KERNEL_TYPE_READ_VRAM
|
2024-11-29 17:15:19 +04:00 |
|
|
Lizonghang
|
6934d52d8a
|
graph->nodes[i] => node
|
2024-11-29 17:14:25 +04:00 |
|
|
Lizonghang
|
ce45587ea9
|
correct GB to GiB
|
2024-11-29 11:20:19 +04:00 |
|
|
Lizonghang
|
0f73d12247
|
decrease compute buf from available memory
|
2024-11-29 11:15:54 +04:00 |
|
|
Lizonghang
|
329d084061
|
add illustration for memory allocation of activations
|
2024-11-29 10:34:21 +04:00 |
|
|
Lizonghang
|
45a1e55eec
|
reduce kv cache from available memory
|
2024-11-28 20:21:21 +04:00 |
|
|
Lizonghang
|
9858d90ce4
|
get system readahead size automatically
|
2024-11-28 16:18:41 +04:00 |
|
|
Lizonghang
|
9a7bbce7ad
|
fix t_load_us
|
2024-11-28 15:55:21 +04:00 |
|
|
Lizonghang
|
740f7f0b95
|
use multithread disk r/w test
|
2024-11-27 22:14:17 +04:00 |
|
|
Lizonghang
|
f7507ec20b
|
fix disk r/w test, add disk access latency, and correct units (GB, GiB)
|
2024-11-27 21:36:12 +04:00 |
|
|
Lizonghang
|
9cd22177d0
|
remove arg test_file
|
2024-11-27 21:34:45 +04:00 |
|
|
Lizonghang
|
0a91ad3edc
|
fix cuda compatibility errors
|
2024-11-26 22:35:58 +04:00 |
|
|
Zonghang Li
|
3f008f2ad9
|
add op GGML_OP_READ
|
2024-11-26 22:28:34 +04:00 |
|
|
Zonghang Li
|
f78c437172
|
add device_inp_embd_delay test, device_memory_bw test, device_cuda_memory_bw test,
|
2024-11-26 22:28:02 +04:00 |
|
|
Lizonghang
|
a7a95b53fe
|
add q80xf32 and count_n_params
|
2024-11-24 23:11:12 +04:00 |
|
|
Lizonghang
|
3fe00a16a0
|
count model flops for f32xf32, f16xf32, q4kxf32, q6kxf32
|
2024-11-24 13:13:32 +04:00 |
|
|
Lizonghang
|
a5ba34169a
|
add f32, f16, q4k_f32, q6k_f32 flops test and fix duplicate inp_embd in subgraphs
|
2024-11-23 21:36:34 +04:00 |
|
|
Zonghang Li
|
7ee1423006
|
add model_flops
|
2024-11-21 20:06:16 +04:00 |
|