Support Mixtral quantization using HQT #67
Closed
Conversation
This file contains hidden or 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
…use of matmul class
dudilester
requested review from
HolyFalafel,
MrGeva,
Yantom1,
nirda7 and
bgoldberg-habana
|
Wrapped the habana static_fused_moe function using a Class |
nirda7
reviewed
Jun 24, 2024
| final_hidden_states += current_hidden_states_static | ||
|
|
||
| return final_hidden_states.view(-1, D) | ||
| class MoeMatmul(nn.Module): |
There was a problem hiding this comment.
Better call it MoeLinear as it more acts like a linear than a matmul
Conflicts:
vllm/hpu/ops.py
Initial FP8 support
dudilester
force-pushed
the
dev/dlester/mixtral_hqt
branch
from
5d9f4de to
e814a4a
Compare
It causes OOM on 70b
Co-authored-by: Krzysztof Laskowski <klaskowski@habana.ai>
dudilester
force-pushed
the
dev/dlester/mixtral_hqt
branch
from
e814a4a to
f4f3437
Compare
dudilester
force-pushed
the
dev/dlester/mixtral_hqt
branch
from
f4f3437 to
87d95ad
Compare
michalkuligowski
added a commit
that referenced
this pull request
Jan 15, 2025
remove expert_max hard code (#47) vLLM-Ext: Full enabling of ALiBi (#34) Add version inference via setuptools-scm (#58) Revert "vLLM-Ext: Full enabling of ALiBi (#34)" (#59) Remove punica_hpu.py from vllm_hpu_extension (#66) Removed previous (not-pipelined) pa implementation (#72) Add flag to enable running softmax in fp32 (#71) Update calibration readme link (#73) allow lm_head quantization in calibration process (#65) Pad to bmin if value is less (#67) Update pyproject.toml (#75) --------- Co-authored-by: Michał Kuligowski <mkuligowski@habana.ai>
mfylcek
added a commit
that referenced
this pull request
Jan 21, 2025
remove expert_max hard code (#47) vLLM-Ext: Full enabling of ALiBi (#34) Add version inference via setuptools-scm (#58) Revert "vLLM-Ext: Full enabling of ALiBi (#34)" (#59) Remove punica_hpu.py from vllm_hpu_extension (#66) Removed previous (not-pipelined) pa implementation (#72) Add flag to enable running softmax in fp32 (#71) Update calibration readme link (#73) allow lm_head quantization in calibration process (#65) Pad to bmin if value is less (#67) Update pyproject.toml (#75) --------- Co-authored-by: Michał Kuligowski <mkuligowski@habana.ai>
yangulei
added a commit
to yangulei/vllm-fork
that referenced
this pull request
Mar 7, 2025
* fix server crash when the client use random seed sampling * fix lint
yangulei
added a commit
to yangulei/vllm-fork
that referenced
this pull request
Mar 11, 2025
* fix server crash when the client use random seed sampling * fix lint
ranzhejiang
pushed a commit
to ranzhejiang/vllm-fork
that referenced
this pull request
Apr 11, 2025
* fix server crash when the client use random seed sampling * fix lint
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.
No description provided.