feat: async + parallel spec dec trtllm example #2091
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
jain-ria
force-pushed
the
rjain/trtllm-spec-dec
branch
4 times, most recently
from
d4a419b to
103a3ad
Compare
jain-ria
requested review from
GuanLuo,
alec-flowers,
biswapanda,
grahamking,
ishandhanani,
jthomson04,
kkranen,
nnshah1,
paulhendricks,
piotrm-nvidia,
ptarasiewiczNV,
rmccorm4,
ryanolson,
tanmayv25,
tedzhouhk and
tmonty12
as code owners
jain-ria
force-pushed
the
rjain/trtllm-spec-dec
branch
from
810b3d8 to
c6ad300
Compare
jain-ria
force-pushed
the
rjain/trtllm-spec-dec
branch
from
0d66e21 to
7868600
Compare
Signed-off-by: jain-ria <riajain@NVIDIA.com>
Signed-off-by: jain-ria <riajain@NVIDIA.com>
…dynamo into rjain/trtllm-spec-dec
jain-ria
force-pushed
the
rjain/trtllm-spec-dec
branch
4 times, most recently
from
6deadce to
9e929ab
Compare
jain-ria
force-pushed
the
rjain/trtllm-spec-dec
branch
from
9e929ab to
e9b5a41
Compare
tanmayv25
reviewed
Aug 13, 2025
| draft_tokens.extend(chunk_data.get("token_ids", [])) | ||
| if len(draft_tokens) >= self.max_draft_len: | ||
| break | ||
| print(f"DRAFTER: {draft_tokens}\n") |
Contributor
There was a problem hiding this comment.
Use logging instead of print.
components/backends/trtllm/src/dynamo/trtllm/utils/api_drafter.py
Outdated
Show resolved
Hide resolved
| ) | ||
| namespace, component, endpoint = parts | ||
|
|
||
| # create minimal runtime for client access only |
Contributor
There was a problem hiding this comment.
Why is this necessary? why not create an endpoint client like this?
| export NUM_DRAFTERS=2 | ||
| export DRAFTER_CUDA_VISIBLE_DEVICES:-"1,2" | ||
| ./launch/spec_dec.sh | ||
| ``` No newline at end of file |
Contributor
There was a problem hiding this comment.
Can you describe the request flow in this setup as well?
Contributor
There was a problem hiding this comment.
May be a mermaid diagram?
jain-ria
changed the title
jain-ria
force-pushed
the
rjain/trtllm-spec-dec
branch
from
a2a6f28 to
16a418e
Compare
jain-ria
force-pushed
the
rjain/trtllm-spec-dec
branch
from
16a418e to
cc7b21a
Compare
|
This PR is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days. |
|
This PR has been closed due to inactivity. If you believe this PR is still relevant, please feel free to reopen it with additional context or information. |
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.
Overview:
Details:
Where should the reviewer start?
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
Summary by CodeRabbit
New Features
Chores