Skip to content

[https://nvbugs/6485390][fix] Fix Qwen disagg throughput regression by restoring MTP forward hook #16740

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
trtllm-agent wants to merge 1 commit into from
Closed

[https://nvbugs/6485390][fix] Fix Qwen disagg throughput regression by restoring MTP forward hook #16740

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion tensorrt_llm/_torch/speculative/mtp_dynamic_tree.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -636,7 +636,7 @@ def _relocate_kv_eagerly(self, attn_metadata, batch_size):
# Top-level forward #
# ------------------------------------------------------------------ #
@nvtx_range("mtp_dyn.forward")
def forward(
def _forward_impl(
self,
input_ids,
position_ids,
Expand Down
2 changes: 0 additions & 2 deletions ...ggregated/gb200_gpt-oss-120b-fp4_1k1k_con2048_ctx1_tp1_gen1_dep2_eplb0_mtp0_ccb-NIXL.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,6 @@ worker_config:
cache_transceiver_config:
max_tokens_in_buffer: 1024
backend: NIXL
transceiver_runtime: PYTHON
disable_overlap_scheduler: true
num_postprocess_workers: 4
stream_interval: 20
Expand All @@ -91,5 +90,4 @@ worker_config:
cache_transceiver_config:
max_tokens_in_buffer: 1024
backend: NIXL
transceiver_runtime: PYTHON
disable_overlap_scheduler: true
Loading