Skip to content

docs: Qwen3-235B-A22B-FP8: remove unnecessary disaggregation strategy argument, and add this model to README #4399

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

Open
Elnifio wants to merge 2 commits into
base: main
Choose a base branch
from
Open

docs: Qwen3-235B-A22B-FP8: remove unnecessary disaggregation strategy argument, and add this model to README #4399

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6cd10da
removes unnecessary strategy
Elnifio Nov 17, 2025
fdc4659
updates README
Elnifio Nov 17, 2025
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
4 changes: 3 additions & 1 deletion recipes/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,8 @@ This repository contains production-ready recipes for deploying large language m
| deepseek-r1 | sglang | disagg (1 node, wide-ep) | 8x H200 | ✅ | 🚧 |🚧 |
| deepseek-r1 | sglang | disagg (multi-node, wide-ep) | 16x H200 | ✅ | 🚧 |🚧 |
| gpt-oss-120b | trtllm | agg | 4x GB200 | ✅ | ✅ |🚧 |
| Qwen3-235B-A22B | trtllm | agg | 16x H200 | ✅ | ✅ |🚧 |
| Qwen3-235B-A22B | trtllm | disagg | 16x H200 | ✅ | ✅ |🚧 |

**Legend:**
- ✅ Functional
Expand Down Expand Up @@ -294,4 +296,4 @@ kubectl wait --for=condition=Complete job/$PERF_JOB_NAME -n $NAMESPACE --timeout
```bash
# Check final benchmark results
kubectl logs job/$PERF_JOB_NAME -n $NAMESPACE | tail -50
```
```
6 changes: 2 additions & 4 deletions recipes/qwen3-235b-a22b-fp8/trtllm/disagg/deploy.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,8 +128,7 @@ spec:
--model-path "${MODEL_PATH}" \
--served-model-name "Qwen/Qwen3-235B-A22B-FP8" \
--extra-engine-args "${ENGINE_ARGS}" \
--disaggregation-mode prefill \
--disaggregation-strategy prefill_first
--disaggregation-mode prefill
volumeMounts:
- name: prefill-config
mountPath: /engine_configs
Expand Down Expand Up @@ -180,8 +179,7 @@ spec:
--model-path "${MODEL_PATH}" \
--served-model-name "Qwen/Qwen3-235B-A22B-FP8" \
--extra-engine-args "${ENGINE_ARGS}" \
--disaggregation-mode decode \
--disaggregation-strategy prefill_first
--disaggregation-mode decode
volumeMounts:
- name: decode-config
mountPath: /engine_configs
Expand Down
Loading