Closed devidw closed 11 months ago
mgolub2
commented
11 months ago I have a similar error: CUDA error 716 at ggml-cuda.cu:6835: misaligned address
Using 1 or 2 4090s. Several models, tried shiningvaliant 70B and a 20B model.
Interestingly, if I don't offload all the layers to the GPU, I don't see the same issue and generation works fine. I checked out the main branch about 20 minutes ago - on commit 6bb4908a17150b49373b5f977685b2e180a04f6f
ggerganov
commented
11 months ago Can you find which commit breaks it?
mgolub2
commented
11 months ago Will try - I'm now getting a segfault instead, after disabling IOMMU and AMD virtualization. I noticed in my kernel messages that when I got the addresss boundary error, there was a bunch of lines with the following:
nvidia 0000:09:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT 
KerfuffleV2
commented
11 months ago edit: Seems like the line numbers for the misaligned address failure are different so maybe this isn't the same. CUDA error 716 at ggml-cuda.cu:7104: misaligned address
Seems like TheBloke also has this issue: https://huggingface.co/TheBloke/Nous-Capybara-34B-GGUF/discussions/1#6553acc8e231fbb2edc30285
Seems like it's just for Yi-based models. He said:
One system has 8 x A6000 - but I'm limiting it to a single GPU using CUDA_VISIBLE_DEVICES. The other a single H100. Both are on CUDA 11.8.
Every generation using -ngl X fails with the error shown before, on those two models. I've not tested other Yi models yet, but other models (Llama 2 13B, Mistral 7B, etc) work fine on the same systems.
Those models work for me on ROCM though I can only offload a few layers.
mgolub2
commented
11 months ago Okay, I don't have any clue what is happening - currently on commit 48ade94538fa509465d71023e49d07aab0ec8cd5
I'm also not using any Yi derived models.
I was able to get the shiningvaliant model to run again, but it only produced junk output (mostly ###) - an issue I was having before checking out the latest code - I had figured it was related to upgrading to cuda 12.3 from 12.1. After purging my system of 12.3 drivers and cuda stuff, I installed 12.1 again via Nvidia's run file, and tried the shiningvalient model.
That's when I got the CUDA error 716 at ggml-cuda.cu:6835: misaligned address error - which eventually I tracked down to having AMDs virtualization on (possibly? it was working with it on before, I thought...). After setting amd_iommu=off, I started getting segfaults instead with commit 6bb4908a17150b49373b5f977685b2e180a04f6f - on 48ade94538fa509465d71023e49d07aab0ec8cd5, both models I was testing produce ######## as the only output.
Now for the scary part - either my system is very broken, in a very bad way, or, llama.cpp is corrupting model files on loading them!! I downloaded a fresh copy of shiningvaliant - and ran md5sum:
mgolub2@4090 /m/p/models> md5sum shiningvaliant-1.2.Q4_K_M.gguf
f71679c53a4281970fce122736ceabac shiningvaliant-1.2.Q4_K_M.ggufI tried running the model in llama.cpp, got ##### for the output again - checked md5sum again and....
mgolub2@4090 /m/p/models> md5sum shiningvaliant-1.2.Q4_K_M.gguf
2994b05523341e4007122660595fbf06 shiningvaliant-1.2.Q4_K_M.ggufAlmost every time I run llama.cpp, the file hash changes. If I don't run llama.cpp, come back an hour later, the hash is fine, so I don't think my brand new SSD(s, I tried a PCIE4 one and an optane one...) are corrupting the data.
So, that's extremely not great - unless this is expected? Does llama.cpp modify the file each run?
Hopefully it's my system being utterly broken? Though I would think memory corruption/disk corruption that bad would just crash linux/windows pretty fast.
mgolub2
commented
11 months ago As an addendum, I re-downloaded shiningvaliant-1.2.Q4_K_M.gguf, and calculated the md5sum again - matches the first time I ran it. removing -ngl from my command, the models works fine, and checking the hash again, it is still the original f71679c hash.
Running with -ngl, I got the same ##### output issue I was having, and the file now hashes to 1d39f46d03d6218e98f8775d91984834 - so the corruption itself is not repeatable either.
Running the now corrupted file without -ngl results in the similar (but different!) broken output with -ngl, so the file is damaged now.
(Is my system super broken?)
mgolub2
commented
11 months ago Okay, sorry to spam so many comments, but I think the issue has to be memory corruption on my system (in the gpu memory?!) !!!
I did the following:
mgolub2@4090 /mnt> sudo umount /mnt/p4
[sudo] password for mgolub2:
mgolub2@4090 /mnt> sudo mount -o ro /mnt/p4
mgolub2@4090 /mnt> ls /mnt/p4/
models
mgolub2@4090 /mnt> touch /mnt/p4/te
touch: cannot touch '/mnt/p4/te': Read-only file system
mgolub2@4090 /mnt [1]> cd /mnt/p4/models/
mgolub2@4090 /m/p/models> md5sum shiningvaliant-1.2.Q4_K_M.gguf
f71679c53a4281970fce122736ceabac shiningvaliant-1.2.Q4_K_M.gguf
mgolub2@4090 /m/p/models> md5sum shiningvaliant-1.2.Q4_K_M.gguf # <- post running llama.cpp
91b594919be553bdeead16c0c046d4be shiningvaliant-1.2.Q4_K_M.gguf
mgolub2@4090 /m/p/models> I have no idea how the hash changes on a read only filesystem. llama.cpp was run as a normal user, not root, not that it should matter.
kallewoof
commented
11 months ago 4760e7cc0b68570d58f55e8dda469805d1759d0d is the first bad commit
commit 4760e7cc0b68570d58f55e8dda469805d1759d0d
Author: Georgi Gerganov <ggerganov@gmail.com>
Date: Mon Nov 13 14:16:23 2023 +0200
sync : ggml (backend v2) (#3912)
* sync : ggml (backend v2) (wip)
* sync : migrate examples and llama.cpp to dynamic graphs (wip)
* sync : update tests + fix max op params to 64
ggml-ci
* sync : ggml-cuda
ggml-ci
* llama : fix save/load state context size
ggml-ci
* sync : try to fix build on tvOS
* sync : pass custom graph sizes in training examples
* sync : update graph copies to new ggml API
* sync : update sync-ggml.sh with new files
* scripts : fix header in sync script
* train : fix context size calculations
* llama : increase inference graph size up to 4096 nodes
* train : allocate grads for backward graphs
* train : allocate grads for gb_tmp
common/train.cpp | 1 +
common/train.h | 2 +
examples/benchmark/benchmark-matmult.cpp | 21 +-
examples/export-lora/export-lora.cpp | 4 +-
examples/finetune/finetune.cpp | 23 +-
examples/llava/clip.cpp | 2 +-
examples/metal/metal.cpp | 10 +-
.../train-text-from-scratch.cpp | 23 +-
ggml-alloc.c | 586 +++++++----
ggml-alloc.h | 84 +-
ggml-backend-impl.h | 87 ++
ggml-backend.c | 591 ++++++++++-
ggml-backend.h | 147 ++-
ggml-cuda.cu | 16 +-
ggml-impl.h | 14 +-
ggml-metal.m | 25 +-
ggml.c | 1047 ++++++++++++--------
ggml.h | 89 +-
llama.cpp | 40 +-
scripts/sync-ggml.sh | 12 +-
tests/test-grad0.cpp | 7 +-
tests/test-opt.cpp | 11 +-
22 files changed, 1986 insertions(+), 856 deletions(-)
create mode 100644 ggml-backend-impl.hNot used to using cuda-gdb, but:
USER: Explain quantum physics. ASSISTANT: 田间
CUDA Exception: Warp Misaligned Address
The exception was triggered at PC 0x7fff9ea56d50
Thread 1 "main" received signal CUDA_EXCEPTION_6, Warp Misaligned Address.
[Switching focus to CUDA kernel 473, grid 4598, block (0,0,0), thread (800,0,0), device 0, sm 0, warp 25, lane 0]
0x00007fff9ea56c80 in void rms_norm_f32<1024>(float const*, float*, int, float)<<<(1,1,1),(1024,1,1)>>> ()
(cuda-gdb) bt
#0 0x00007fff9ea56c80 in void rms_norm_f32<1024>(float const*, float*, int, float)<<<(1,1,1),(1024,1,1)>>> ()Okay, sorry to spam so many comments, but I think the issue has to be memory corruption on my system (in the gpu memory?!) !!!
I did the following:
mgolub2@4090 /mnt> sudo umount /mnt/p4 [sudo] password for mgolub2: mgolub2@4090 /mnt> sudo mount -o ro /mnt/p4 mgolub2@4090 /mnt> ls /mnt/p4/ models mgolub2@4090 /mnt> touch /mnt/p4/te touch: cannot touch '/mnt/p4/te': Read-only file system mgolub2@4090 /mnt [1]> cd /mnt/p4/models/ mgolub2@4090 /m/p/models> md5sum shiningvaliant-1.2.Q4_K_M.gguf f71679c53a4281970fce122736ceabac shiningvaliant-1.2.Q4_K_M.gguf mgolub2@4090 /m/p/models> md5sum shiningvaliant-1.2.Q4_K_M.gguf # <- post running llama.cpp 91b594919be553bdeead16c0c046d4be shiningvaliant-1.2.Q4_K_M.gguf mgolub2@4090 /m/p/models>I have no idea how the hash changes on a read only filesystem. llama.cpp was run as a normal user, not root, not that it should matter.
Ah - mmap strikes again. Rebooting the system after passing memtest, the file is now back to it's original hash - though I bet if the disk is mounted rw, this corruption would persist as the changes would get synced back to the filesystem? I'm not well versed in how mmap works.
4760e7cc0b68570d58f55e8dda469805d1759d0d is the first bad commit commit 4760e7cc0b68570d58f55e8dda469805d1759d0d Author: Georgi Gerganov <ggerganov@gmail.com> Date: Mon Nov 13 14:16:23 2023 +0200 sync : ggml (backend v2) (#3912) * sync : ggml (backend v2) (wip) * sync : migrate examples and llama.cpp to dynamic graphs (wip) * sync : update tests + fix max op params to 64 ggml-ci * sync : ggml-cuda ggml-ci * llama : fix save/load state context size ggml-ci * sync : try to fix build on tvOS * sync : pass custom graph sizes in training examples * sync : update graph copies to new ggml API * sync : update sync-ggml.sh with new files * scripts : fix header in sync script * train : fix context size calculations * llama : increase inference graph size up to 4096 nodes * train : allocate grads for backward graphs * train : allocate grads for gb_tmp common/train.cpp | 1 + common/train.h | 2 + examples/benchmark/benchmark-matmult.cpp | 21 +- examples/export-lora/export-lora.cpp | 4 +- examples/finetune/finetune.cpp | 23 +- examples/llava/clip.cpp | 2 +- examples/metal/metal.cpp | 10 +- .../train-text-from-scratch.cpp | 23 +- ggml-alloc.c | 586 +++++++---- ggml-alloc.h | 84 +- ggml-backend-impl.h | 87 ++ ggml-backend.c | 591 ++++++++++- ggml-backend.h | 147 ++- ggml-cuda.cu | 16 +- ggml-impl.h | 14 +- ggml-metal.m | 25 +- ggml.c | 1047 ++++++++++++-------- ggml.h | 89 +- llama.cpp | 40 +- scripts/sync-ggml.sh | 12 +- tests/test-grad0.cpp | 7 +- tests/test-opt.cpp | 11 +- 22 files changed, 1986 insertions(+), 856 deletions(-) create mode 100644 ggml-backend-impl.h
I can confirm this commit is problematic, though it causes a different issue for me: CUDA error 700 at ggml-cuda.cu:6838: an illegal memory access was encountered current device: 0
ggerganov
commented
11 months ago @TheBloke @devidw @kallewoof @mgolub2 Could you please confirm that #4048 fixes the issue?
TheBloke
commented
11 months ago Yes it does! Thank you
(it's #4084 BTW)
devidw
commented
11 months ago Yeah, can confirm also, thx 🙏
$ make serve
./llama.cpp/server \
-m ~/models/models--TheBloke--OpenHermes-2.5-Mistral-7B-GGUF/snapshots/5682e25bb033d9d21f6d159859e21df4552c1f26/openhermes-2.5-mistral-7b.Q2_K.gguf \
-c 2048 \
--threads 1 \
--n-gpu-layers 83
ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
Device 0: NVIDIA H100 PCIe, compute capability 9.0
{"timestamp":1700049283,"level":"INFO","function":"main","line":2268,"message":"build info","build":1517,"commit":"b4a36f4"}
{"timestamp":1700049283,"level":"INFO","function":"main","line":2271,"message":"system info","n_threads":1,"n_threads_batch":-1,"total_threads":26,"system_info":"AVX = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | "}
llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from /home/ubuntu/models/models--TheBloke--OpenHermes-2.5-Mistral-7B-GGUF/snapshots/5682e25bb033d9d21f6d159859e21df4552c1f26/openhermes-2.5-mistral-7b.Q2_K.gguf (version GGUF V3 (latest))
llama_model_loader: - tensor 0: token_embd.weight q2_K [ 4096, 32002, 1, 1 ]
llama_model_loader: - tensor 1: blk.0.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 2: blk.0.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 3: blk.0.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 4: blk.0.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 5: blk.0.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 6: blk.0.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 7: blk.0.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 8: blk.0.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 9: blk.0.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 10: blk.1.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 11: blk.1.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 12: blk.1.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 13: blk.1.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 14: blk.1.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 15: blk.1.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 16: blk.1.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 17: blk.1.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 18: blk.1.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 19: blk.2.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 20: blk.2.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 21: blk.2.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 22: blk.2.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 23: blk.2.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 24: blk.2.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 25: blk.2.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 26: blk.2.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 27: blk.2.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 28: blk.3.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 29: blk.3.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 30: blk.3.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 31: blk.3.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 32: blk.3.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 33: blk.3.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 34: blk.3.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 35: blk.3.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 36: blk.3.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 37: blk.4.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 38: blk.4.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 39: blk.4.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 40: blk.4.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 41: blk.4.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 42: blk.4.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 43: blk.4.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 44: blk.4.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 45: blk.4.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 46: blk.5.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 47: blk.5.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 48: blk.5.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 49: blk.5.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 50: blk.5.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 51: blk.5.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 52: blk.5.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 53: blk.5.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 54: blk.5.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 55: blk.6.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 56: blk.6.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 57: blk.6.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 58: blk.6.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 59: blk.6.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 60: blk.6.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 61: blk.6.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 62: blk.6.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 63: blk.6.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 64: blk.7.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 65: blk.7.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 66: blk.7.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 67: blk.7.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 68: blk.7.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 69: blk.7.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 70: blk.7.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 71: blk.7.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 72: blk.7.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 73: blk.8.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 74: blk.8.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 75: blk.8.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 76: blk.8.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 77: blk.8.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 78: blk.8.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 79: blk.8.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 80: blk.8.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 81: blk.8.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 82: blk.9.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 83: blk.9.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 84: blk.9.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 85: blk.9.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 86: blk.9.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 87: blk.9.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 88: blk.9.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 89: blk.9.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 90: blk.9.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 91: blk.10.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 92: blk.10.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 93: blk.10.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 94: blk.10.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 95: blk.10.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 96: blk.10.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 97: blk.10.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 98: blk.10.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 99: blk.10.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 100: blk.11.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 101: blk.11.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 102: blk.11.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 103: blk.11.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 104: blk.11.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 105: blk.11.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 106: blk.11.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 107: blk.11.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 108: blk.11.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 109: blk.12.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 110: blk.12.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 111: blk.12.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 112: blk.12.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 113: blk.12.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 114: blk.12.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 115: blk.12.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 116: blk.12.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 117: blk.12.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 118: blk.13.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 119: blk.13.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 120: blk.13.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 121: blk.13.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 122: blk.13.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 123: blk.13.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 124: blk.13.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 125: blk.13.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 126: blk.13.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 127: blk.14.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 128: blk.14.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 129: blk.14.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 130: blk.14.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 131: blk.14.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 132: blk.14.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 133: blk.14.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 134: blk.14.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 135: blk.14.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 136: blk.15.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 137: blk.15.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 138: blk.15.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 139: blk.15.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 140: blk.15.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 141: blk.15.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 142: blk.15.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 143: blk.15.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 144: blk.15.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 145: blk.16.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 146: blk.16.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 147: blk.16.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 148: blk.16.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 149: blk.16.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 150: blk.16.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 151: blk.16.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 152: blk.16.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 153: blk.16.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 154: blk.17.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 155: blk.17.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 156: blk.17.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 157: blk.17.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 158: blk.17.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 159: blk.17.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 160: blk.17.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 161: blk.17.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 162: blk.17.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 163: blk.18.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 164: blk.18.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 165: blk.18.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 166: blk.18.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 167: blk.18.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 168: blk.18.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 169: blk.18.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 170: blk.18.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 171: blk.18.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 172: blk.19.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 173: blk.19.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 174: blk.19.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 175: blk.19.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 176: blk.19.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 177: blk.19.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 178: blk.19.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 179: blk.19.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 180: blk.19.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 181: blk.20.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 182: blk.20.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 183: blk.20.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 184: blk.20.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 185: blk.20.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 186: blk.20.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 187: blk.20.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 188: blk.20.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 189: blk.20.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 190: blk.21.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 191: blk.21.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 192: blk.21.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 193: blk.21.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 194: blk.21.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 195: blk.21.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 196: blk.21.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 197: blk.21.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 198: blk.21.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 199: blk.22.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 200: blk.22.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 201: blk.22.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 202: blk.22.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 203: blk.22.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 204: blk.22.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 205: blk.22.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 206: blk.22.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 207: blk.22.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 208: blk.23.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 209: blk.23.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 210: blk.23.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 211: blk.23.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 212: blk.23.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 213: blk.23.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 214: blk.23.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 215: blk.23.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 216: blk.23.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 217: blk.24.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 218: blk.24.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 219: blk.24.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 220: blk.24.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 221: blk.24.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 222: blk.24.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 223: blk.24.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 224: blk.24.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 225: blk.24.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 226: blk.25.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 227: blk.25.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 228: blk.25.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 229: blk.25.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 230: blk.25.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 231: blk.25.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 232: blk.25.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 233: blk.25.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 234: blk.25.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 235: blk.26.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 236: blk.26.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 237: blk.26.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 238: blk.26.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 239: blk.26.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 240: blk.26.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 241: blk.26.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 242: blk.26.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 243: blk.26.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 244: blk.27.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 245: blk.27.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 246: blk.27.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 247: blk.27.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 248: blk.27.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 249: blk.27.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 250: blk.27.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 251: blk.27.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 252: blk.27.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 253: blk.28.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 254: blk.28.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 255: blk.28.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 256: blk.28.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 257: blk.28.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 258: blk.28.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 259: blk.28.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 260: blk.28.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 261: blk.28.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 262: blk.29.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 263: blk.29.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 264: blk.29.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 265: blk.29.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 266: blk.29.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 267: blk.29.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 268: blk.29.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 269: blk.29.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 270: blk.29.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 271: blk.30.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 272: blk.30.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 273: blk.30.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 274: blk.30.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 275: blk.30.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 276: blk.30.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 277: blk.30.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 278: blk.30.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 279: blk.30.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 280: blk.31.attn_q.weight q2_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 281: blk.31.attn_k.weight q2_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 282: blk.31.attn_v.weight q3_K [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 283: blk.31.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 284: blk.31.ffn_gate.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 285: blk.31.ffn_up.weight q3_K [ 4096, 14336, 1, 1 ]
llama_model_loader: - tensor 286: blk.31.ffn_down.weight q3_K [ 14336, 4096, 1, 1 ]
llama_model_loader: - tensor 287: blk.31.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 288: blk.31.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 289: output_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 290: output.weight q6_K [ 4096, 32002, 1, 1 ]
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: general.name str
llama_model_loader: - kv 2: llama.context_length u32
llama_model_loader: - kv 3: llama.embedding_length u32
llama_model_loader: - kv 4: llama.block_count u32
llama_model_loader: - kv 5: llama.feed_forward_length u32
llama_model_loader: - kv 6: llama.rope.dimension_count u32
llama_model_loader: - kv 7: llama.attention.head_count u32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32
llama_model_loader: - kv 10: llama.rope.freq_base f32
llama_model_loader: - kv 11: general.file_type u32
llama_model_loader: - kv 12: tokenizer.ggml.model str
llama_model_loader: - kv 13: tokenizer.ggml.tokens arr
llama_model_loader: - kv 14: tokenizer.ggml.scores arr
llama_model_loader: - kv 15: tokenizer.ggml.token_type arr
llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32
llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32
llama_model_loader: - kv 18: tokenizer.ggml.padding_token_id u32
llama_model_loader: - kv 19: general.quantization_version u32
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q2_K: 65 tensors
llama_model_loader: - type q3_K: 160 tensors
llama_model_loader: - type q6_K: 1 tensors
llm_load_vocab: special tokens definition check successful ( 261/32002 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32002
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 32768
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_gqa = 4
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff = 14336
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 32768
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = mostly Q2_K
llm_load_print_meta: model params = 7.24 B
llm_load_print_meta: model size = 2.87 GiB (3.41 BPW)
llm_load_print_meta: general.name = teknium_openhermes-2.5-mistral-7b
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 32000 '<|im_end|>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 0 '<unk>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.11 MB
llm_load_tensors: using CUDA for GPU acceleration
llm_load_tensors: mem required = 41.12 MB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 35/35 layers to GPU
llm_load_tensors: VRAM used: 2898.56 MB
.................................................................................................
llama_new_context_with_model: n_ctx = 2048
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: offloading v cache to GPU
llama_kv_cache_init: offloading k cache to GPU
llama_kv_cache_init: VRAM kv self = 256.00 MB
llama_new_context_with_model: kv self size = 256.00 MB
llama_build_graph: non-view tensors processed: 740/740
llama_new_context_with_model: compute buffer total size = 157.57 MB
llama_new_context_with_model: VRAM scratch buffer: 156.00 MB
llama_new_context_with_model: total VRAM used: 3310.57 MB (model: 2898.56 MB, context: 412.00 MB)
Available slots:
-> Slot 0 - max context: 2048
llama server listening at http://127.0.0.1:8080
{"timestamp":1700049284,"level":"INFO","function":"main","line":2548,"message":"HTTP server listening","hostname":"127.0.0.1","port":8080}
all slots are idle and system prompt is empty, clear the KV cache
slot 0 is processing [task id: 0]
slot 0 : kv cache rm - [0, end)
print_timings: prompt eval time = 66.75 ms / 2 tokens ( 33.37 ms per token, 29.96 tokens per second)
print_timings: eval time = 4759.53 ms / 328 runs ( 14.51 ms per token, 68.91 tokens per second)
print_timings: total time = 4826.28 ms
slot 0 released (331 tokens in cache)
{"timestamp":1700049296,"level":"INFO","function":"log_server_request","line":2212,"message":"request","remote_addr":"127.0.0.1","remote_port":56320,"status":200,"method":"POST","path":"/completion","params":{}}Yeah, fix works for me.
Prerequisites
Please answer the following questions for yourself before submitting an issue.
Expected Behavior
run model server on h100 or a100 gpu (tried both)
Current Behavior
server dies with
CUDA error 716 at ggml-cuda.cu:7546: misaligned addresson first incoming jobEnvironment and Context
Please provide detailed information about your computer setup. This is important in case the issue is not reproducible except for under certain specific conditions.
$ lscpu$ uname -aFailure Information (for bugs)
Please help provide information about the failure / bug.
Steps to Reproduce
Please provide detailed steps for reproducing the issue. We are not sitting in front of your screen, so the more detail the better.
make clean && LLAMA_CUBLAS=1 make -jFailure Logs