Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ schema: 2
name: qwen35-b200-fp8-agentx-disagg-1p1d-p-tp4-d-tp4-hicache-c16-mtp
model:
path: qwen3.5-fp8
container: lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85
container: lmsysorg/sglang:nightly-dev-cu13-20261001-b37e6f79@sha256:65a8507b99dc1a6ebfc72344f29cbc017bffd5972ff53bc2d5f43aa293c88a84
precision: fp8
engine: sglang
dynamo:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ schema: 2
name: qwen35-b200-fp8-agentx-disagg-1p1d-p-tp4-d-tp4-hicache-c24-mtp
model:
path: qwen3.5-fp8
container: lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85
container: lmsysorg/sglang:nightly-dev-cu13-20261001-b37e6f79@sha256:65a8507b99dc1a6ebfc72344f29cbc017bffd5972ff53bc2d5f43aa293c88a84
precision: fp8
engine: sglang
dynamo:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ schema: 2
name: qwen35-b200-fp8-agentx-disagg-1p1d-p-tp4-d-tp4-hicache-c32-mtp
model:
path: qwen3.5-fp8
container: lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85
container: lmsysorg/sglang:nightly-dev-cu13-20261001-b37e6f79@sha256:65a8507b99dc1a6ebfc72344f29cbc017bffd5972ff53bc2d5f43aa293c88a84
precision: fp8
engine: sglang
dynamo:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ schema: 2
name: qwen35-b200-fp8-agentx-disagg-1p1d-p-tp4-d-tp4-hicache-c48-write-through-mtp
model:
path: qwen3.5-fp8
container: lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85
container: lmsysorg/sglang:nightly-dev-cu13-20261001-b37e6f79@sha256:65a8507b99dc1a6ebfc72344f29cbc017bffd5972ff53bc2d5f43aa293c88a84
precision: fp8
engine: sglang
dynamo:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ schema: 2
name: qwen35-b200-fp8-agentx-disagg-1p1d-p-tp4-d-tp4-hicache-c64-write-through-mtp
model:
path: qwen3.5-fp8
container: lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85
container: lmsysorg/sglang:nightly-dev-cu13-20261001-b37e6f79@sha256:65a8507b99dc1a6ebfc72344f29cbc017bffd5972ff53bc2d5f43aa293c88a84
precision: fp8
engine: sglang
dynamo:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ schema: 2
name: qwen35-b200-fp8-agentx-disagg-1p1d-p-tp4-d-tp4-hicache-c8-mtp
model:
path: qwen3.5-fp8
container: lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85
container: lmsysorg/sglang:nightly-dev-cu13-20261001-b37e6f79@sha256:65a8507b99dc1a6ebfc72344f29cbc017bffd5972ff53bc2d5f43aa293c88a84
precision: fp8
engine: sglang
dynamo:
Expand Down
2 changes: 1 addition & 1 deletion inferencex-e2e/configs/nvidia-master.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -8586,7 +8586,7 @@ dsv4-fp4-b200-dynamo-sglang-agentic-disagg:
dp-attn: true

qwen3.5-fp8-b200-dynamo-sglang-agentic-disagg-mtp:
image: lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85
image: lmsysorg/sglang:nightly-dev-cu13-20261001-b37e6f79@sha256:65a8507b99dc1a6ebfc72344f29cbc017bffd5972ff53bc2d5f43aa293c88a84
model: Qwen/Qwen3.5-397B-A17B-FP8
model-prefix: qwen3.5
runner: cluster:b200-nscale
Expand Down
Loading