modification on llamacpp readme after Ipex-llm latest update #11971
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
rnwang04
reviewed
Aug 30, 2024
| llama_new_context_with_model: SYCL_Host compute buffer size = 288.02 MiB | ||
| llama_new_context_with_model: graph nodes = 1062 | ||
| llama_new_context_with_model: graph splits = 2 | ||
| Native API failed. Native API returns: -5 (PI_ERROR_OUT_OF_RESOURCES) -5 (PI_ERROR_OUT_OF_RESOURCES)Exception caught at file:C:/Users/Administrator/actions-runner/cpp-release/_work/llm.cpp/llm.cpp/llama-cpp-bigdl/ggml/src/ggml-sycl.cpp, line:2856 |
| @@ -127,16 +126,12 @@ To use GPU acceleration, several environment variables are required or recommend | |||
|
|
|||
| ```cmd | |||
| set SYCL_CACHE_PERSISTENT=1 | |||
| rem under most circumstances, the following environment variable may improve performance, but sometimes this may also cause performance degradation | |||
|
|
||
| #### 14. `Native API failed` error | ||
| On latest version of `ipex-llm`, you might come across `native API failed` error with certain models without the `-c` parameter. Simply adding `-c 1024` would resolve this problem. |
There was a problem hiding this comment.
On latest version of ipex-llm's llama.cpp, you might come across native API failed error with certain models without the -c parameter. Simply adding -c xx would resolve this problem.
|
|
||
| #### 13. Core dump when having both integrated and dedicated graphics | ||
| If you have both integrated and dedicated graphics on your computer and didn't specify which device to use, it will cause a core dump. Therefore, you need to run `export ONEAPI_DEVICE_SELECTOR=level_zero:0` before running `llama-cli`. |
There was a problem hiding this comment.
If you have both integrated and dedicated graphics displayed in your llama.cpp's device log and don't specify which device to use, it will cause a core dump. In such case, you may need to specify export ONEAPI_DEVICE_SELECTOR=level_zero:0 before running llama-cli.
|
Please also add number for ollama's troubleshooting. |
rnwang04
reviewed
Aug 30, 2024
| ``` | ||
|
|
||
| Under your current directory, you can also execute below command to have interactive chat with Llama3: | ||
|
|
||
| - For **Linux users**: | ||
|
|
||
| ```bash | ||
| ./main -ngl 33 --interactive-first --color -e --in-prefix '<|start_header_id|>user<|end_header_id|>\n\n' --in-suffix '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' -r '<|eot_id|>' -m <model_dir>/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf | ||
| ./llama-cli -ngl 33 --interactive-first --color -e --in-prefix '<|start_header_id|>user<|end_header_id|>\n\n' --in-suffix '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' -r '<|eot_id|>' -m <model_dir>/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf -c 1024 |
There was a problem hiding this comment.
Please confirm if it still works for new llama.cpp
cranechu0131
pushed a commit
to cranechu0131/ipex-llm
that referenced
this pull request
Sep 9, 2024
…nalytics#11971) * update on readme after ipex-llm update * update on readme after ipex-llm update * rebase & delete redundancy * revise * add numbers for troubleshooting
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
@rnwang04