Skip to content

[https://nvbugs/6480621][test] Revert to 60-second KV transfer timeout for GB300 DeepSeek V4 Pro disaggregated perf-sanity #17137

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

Merged
chienchunhung merged 1 commit into from
Aug 28, 2026
Merged

[https://nvbugs/6480621][test] Revert to 60-second KV transfer timeout for GB300 DeepSeek V4 Pro disaggregated perf-sanity #17137

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
7 changes: 5 additions & 2 deletions ...ted/gb300_deepseek-v4-pro-fp4_8k1k_con180_ctx3_dep4_gen1_dep32_eplb384_mtp3_ccb-NIXL.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,9 @@ environment:
server_env_var: TRTLLM_SERVER_DISABLE_GC=1
profiling:
nsys_on: false
# Keep this stage as explicit coverage while the precheck is globally opt-in.
cache_transceiver_precheck:
enabled: true
worker_config:
gen:
print_iter_log: true
Expand All @@ -67,7 +70,7 @@ worker_config:
load_balancer: tests/scripts/perf-sanity/disaggregated/deepseek-v4-pro-eplb/moe_load_balancer_gen_ep32_slots384.yaml
cache_transceiver_config:
max_tokens_in_buffer: 8192
kv_transfer_timeout_ms: 600000
kv_transfer_timeout_ms: 60000
backend: NIXL
transceiver_runtime: PYTHON
disable_overlap_scheduler: false
Expand Down Expand Up @@ -98,7 +101,7 @@ worker_config:
load_balancer: tests/scripts/perf-sanity/disaggregated/deepseek-v4-pro-eplb/moe_load_balancer_ctx_ep4_384.yaml
cache_transceiver_config:
max_tokens_in_buffer: 8192
kv_transfer_timeout_ms: 600000
kv_transfer_timeout_ms: 60000
backend: NIXL
transceiver_runtime: PYTHON
disable_overlap_scheduler: false
Expand Down
Loading