Make config.json consistent between shortfin and sharktank #487
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
stbaione
reviewed
Nov 12, 2024
| return { | ||
| "module_name": "module", | ||
| "module_abi_version": 1, | ||
| "max_seq_len": hp.context_length, | ||
| "attn_head_count": hp.attention_head_count, | ||
| # "attn_head_count": hp.attention_head_count, # we don't need the attention head count we just need the kvcache attention head count for shortfin |
There was a problem hiding this comment.
Since all of the docs are updated and references to "attn_head_count" are removed, this is probably fine to delete. Otherwise, it'll sit here lingering for who knows how long
stbaione
approved these changes
Nov 12, 2024
11 tasks
renxida
force-pushed
the
config-consistency
branch
from
c7b1d3b to
4a1357d
Compare
stbaione
reviewed
Dec 10, 2024
renxida
force-pushed
the
config-consistency
branch
from
2d99109 to
f7490f6
Compare
stbaione
added a commit
that referenced
this pull request
Dec 12, 2024
#676) # Description Did a pass through and made updates + fixes to the user docs for `e2e_llama8b_mi300x.md`. 1. Update install instructions for `shark-ai` 2. Update nightly install instructions for `shortfin` and `sharktank` 3. Update paths for model artifacts to ensure they work with `llama3.1-8b-fp16-instruct` 4. Remove steps to `write edited config`. No longer needed after #487 Added back `sentencepiece` as a requirement for `sharktank`. Not having it caused `export_paged_llm_v1` to break when installing nightly: ```text ModuleNotFoundError: No module named 'sentencepiece' ``` This was obfuscated when building from source, because `shortfin` includes `sentencepiece` in `requirements-tests.txt`.
IanNod
pushed a commit
to IanNod/SHARK-Platform
that referenced
this pull request
Dec 17, 2024
And remove the adaption layer in buidl_tools/integration_tests/llm/conftest.py
IanNod
pushed a commit
to IanNod/SHARK-Platform
that referenced
this pull request
Dec 17, 2024
nod-ai#676) # Description Did a pass through and made updates + fixes to the user docs for `e2e_llama8b_mi300x.md`. 1. Update install instructions for `shark-ai` 2. Update nightly install instructions for `shortfin` and `sharktank` 3. Update paths for model artifacts to ensure they work with `llama3.1-8b-fp16-instruct` 4. Remove steps to `write edited config`. No longer needed after nod-ai#487 Added back `sentencepiece` as a requirement for `sharktank`. Not having it caused `export_paged_llm_v1` to break when installing nightly: ```text ModuleNotFoundError: No module named 'sentencepiece' ``` This was obfuscated when building from source, because `shortfin` includes `sentencepiece` in `requirements-tests.txt`.
monorimet
pushed a commit
that referenced
this pull request
Jan 8, 2025
And remove the adaption layer in buidl_tools/integration_tests/llm/conftest.py
monorimet
pushed a commit
that referenced
this pull request
Jan 8, 2025
#676) # Description Did a pass through and made updates + fixes to the user docs for `e2e_llama8b_mi300x.md`. 1. Update install instructions for `shark-ai` 2. Update nightly install instructions for `shortfin` and `sharktank` 3. Update paths for model artifacts to ensure they work with `llama3.1-8b-fp16-instruct` 4. Remove steps to `write edited config`. No longer needed after #487 Added back `sentencepiece` as a requirement for `sharktank`. Not having it caused `export_paged_llm_v1` to break when installing nightly: ```text ModuleNotFoundError: No module named 'sentencepiece' ``` This was obfuscated when building from source, because `shortfin` includes `sentencepiece` in `requirements-tests.txt`.
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.
And remove the adaption layer in buidl_tools/integration_tests/llm/conftest.py