You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
[x ] I reviewed the Discussions, and have a new bug or useful enhancement to share.
Expected Behavior
Speed was typical 6.3 tokens/sec for Win10, i5850, 32 GB both with supplied main.exe AVX2 up to build 1440
Test confirmed by GCC compiled under CodeBlocks.
Current Behavior
Beginning with Build b1442 (confirmed with b1443, b1444, b1445) speed drops to 2.84 tokens / second under same
test conditions.
Environment and Context
Test done at equal conditions with the following start:
main -t 6 -m models/META-2/7B/META_2_7B_f16_V4_q4_0.gguf --log-disable --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 --in-prefix-bos --in-prefix [INST] --in-suffix [/INST] -i -p "[INST] <> You are a helpful, respectful and honest assistant. <> Write Good Morning in German. [/INST]"
After the complete answer manually stopped by Ctrl C and speed token/sec taken.
Physical (or virtual) hardware you are using, e.g. for Linux:
` i5 8350, 32 GB RAM, 1TB M.2 SSD
Operating System, e.g. for Linux:
`WIN 10, up to date
SDK version, e.g. for Linux:
*Checked CPU only version AVX2 packages: e.g. llama-b1440-bin-win-avx2-x64.zip
Checked with provided b1440, b1442 ... b1445 AVX2 packages (main.exe and dll's from package)
Counter checked with GCC, IDE is CodeBlocks build1440 performs as expected, build 1445 same speed drop as referenced versions
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.
step 1 Unpack build AVX2 dll's and main into clean test environment (root directory drive C:\LLaMa2\0_KI_test)
step 2 start main by batch file
step 3 Wait till system completes response.
step 4 Hit Ctrl C, confirm Yes and take note of tokens/sec
Prerequisites
Please answer the following questions for yourself before submitting an issue.
Expected Behavior
Speed was typical 6.3 tokens/sec for Win10, i5850, 32 GB both with supplied main.exe AVX2 up to build 1440
Test confirmed by GCC compiled under CodeBlocks.
Current Behavior
Beginning with Build b1442 (confirmed with b1443, b1444, b1445) speed drops to 2.84 tokens / second under same
test conditions.
Environment and Context
Test done at equal conditions with the following start:
main -t 6 -m models/META-2/7B/META_2_7B_f16_V4_q4_0.gguf --log-disable --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 --in-prefix-bos --in-prefix [INST] --in-suffix [/INST] -i -p "[INST] <> You are a helpful, respectful and honest assistant. <> Write Good Morning in German. [/INST]"
After the complete answer manually stopped by Ctrl C and speed token/sec taken.
` i5 8350, 32 GB RAM, 1TB M.2 SSD
`WIN 10, up to date
*Checked CPU only version AVX2 packages: e.g. llama-b1440-bin-win-avx2-x64.zip
Checked with provided b1440, b1442 ... b1445 AVX2 packages (main.exe and dll's from package)
Counter checked with GCC, IDE is CodeBlocks build1440 performs as expected, build 1445 same speed drop as referenced versions
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.
Notice speed drop after build 1440 (starting b1442) b1440:
llama-b1440-bin-win-avx2-x64.zip 6.3 tokens/sec,
llama-b1442-bin-win-avx2-x64.zip 2.84 tokens/sec
llama-b1443-bin-win-avx2-x64.zip 2.84 tokens/sec
llama-b1444-bin-win-avx2-x64.zip 2.84 tokens/sec
llama-b1445-bin-win-avx2-x64.zip 2.84 tokens/sec
The text was updated successfully, but these errors were encountered: