Skip to content

Add Kimi-K2.5 vLLM recipes and fix NIXL side channel host #11

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
nlevin-ui merged 2 commits into from
Apr 6, 2026
Merged

Add Kimi-K2.5 vLLM recipes and fix NIXL side channel host #11

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
6eaa774
Add Kimi-K2.5 vLLM recipes and fix NIXL side channel host
nlevin-ui Apr 6, 2026
4efc6e2
ci: run checks on PRs targeting sa-submission-q2-2026
nlevin-ui Apr 6, 2026
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
3 changes: 2 additions & 1 deletion .github/workflows/ci.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ on:
push:
branches: [main, master]
pull_request:
branches: [main, master]
branches: [main, master, sa-submission-q2-2026]

jobs:
lint:
Expand Down Expand Up @@ -119,3 +119,4 @@ jobs:
exit(1)
print(f'\nAll {len(recipes)} recipes valid')
"

101 changes: 101 additions & 0 deletions recipes/vllm/kimi-k2.5/1k1k/disagg-gb200-1p1d-dep4-dep16.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,101 @@
name: "kimi-vllm-disagg-gb200-1p1d-dep4-dep16"

model:
path: "kimi-k2.5-nvfp4"
container: "vllm/vllm-openai:v0.18.0-cu130"
precision: "fp4"

dynamo:
version: 1.0.1
install: true

setup_script: vllm-container-deps.sh

resources:
gpu_type: "gb200"
gpus_per_node: 4
prefill_nodes: 1
decode_nodes: 4
prefill_workers: 1
decode_workers: 1
gpus_per_prefill: 4
gpus_per_decode: 16

frontend:
type: dynamo
enable_multiple_frontends: false

backend:
type: vllm
connector: null

prefill_environment:
VLLM_USE_FLASHINFER_MOE_FP4: "1"
VLLM_USE_NCCL_SYMM_MEM: "1"
NCCL_CUMEM_ENABLE: "1"
NCCL_MNNVL_ENABLE: "1"
NCCL_NVLS_ENABLE: "1"

decode_environment:
VLLM_USE_FLASHINFER_MOE_FP4: "1"
VLLM_USE_NCCL_SYMM_MEM: "1"
NCCL_CUMEM_ENABLE: "1"
NCCL_MNNVL_ENABLE: "1"
NCCL_NVLS_ENABLE: "1"

vllm_config:
prefill:
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
served-model-name: "nvidia/Kimi-K2.5-NVFP4"
kv-cache-dtype: "fp8"
tensor-parallel-size: 1
pipeline-parallel-size: 1
data-parallel-size: 4
data-parallel-rpc-port: 13345
enable-expert-parallel: true
max-model-len: 3072
max-num-seqs: 4096
enforce-eager: true
compilation-config: '{"custom_ops":["+quant_fp8","+rms_norm","+rotary_embedding"],"pass_config":{"fuse_attn_quant":true,"fuse_allreduce_rms":true}}'
max-num-batched-tokens: 16384
safetensors-load-strategy: "prefetch"
trust-remote-code: true
no-enable-prefix-caching: true
no-enable-chunked-prefill: true
attention-backend: "FLASHINFER_MLA"
block-size: 64
attention-config: '{"use_trtllm_ragged_deepseek_prefill": true}'
all2all-backend: "flashinfer_nvlink_one_sided"
gpu-memory-utilization: 0.9

decode:
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
served-model-name: "nvidia/Kimi-K2.5-NVFP4"
kv-cache-dtype: "fp8"
tensor-parallel-size: 1
pipeline-parallel-size: 1
data-parallel-size: 16
data-parallel-rpc-port: 13345
enable-expert-parallel: true
max-model-len: 3072
max-num-seqs: 4096
max-num-batched-tokens: 10240
safetensors-load-strategy: "prefetch"
trust-remote-code: true
no-enable-prefix-caching: true
no-enable-chunked-prefill: true
async-scheduling: true
attention-backend: "FLASHINFER_MLA"
block-size: 64
all2all-backend: "flashinfer_nvlink_one_sided"
compilation-config: '{"cudagraph_mode":"FULL_DECODE_ONLY","custom_ops":["+quant_fp8","+rms_norm","+rotary_embedding"],"pass_config":{"fuse_attn_quant":true,"fuse_allreduce_rms":true}}'
gpu-memory-utilization: 0.9
stream-interval: 50
max-cudagraph-capture-size: 512

benchmark:
type: "sa-bench"
isl: 1024
osl: 1024
concurrencies: "256x512x1024x2048x3072x4096"
req_rate: "inf"
98 changes: 98 additions & 0 deletions recipes/vllm/kimi-k2.5/1k1k/disagg-gb200-1p4d-dep4-tep4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,98 @@
name: "kimi-vllm-disagg-gb200-1p4d-dep4-tep4"

model:
path: "kimi-k2.5-nvfp4"
container: "vllm/vllm-openai:v0.18.0-cu130"
precision: "fp4"

dynamo:
version: 1.0.1
install: true

setup_script: vllm-container-deps.sh

resources:
gpu_type: "gb200"
gpus_per_node: 4
prefill_nodes: 1
decode_nodes: 4
prefill_workers: 1
decode_workers: 4
gpus_per_prefill: 4
gpus_per_decode: 4

frontend:
type: dynamo
enable_multiple_frontends: false

backend:
type: vllm
connector: null

prefill_environment:
VLLM_USE_FLASHINFER_MOE_FP4: "1"
VLLM_USE_NCCL_SYMM_MEM: "1"
NCCL_CUMEM_ENABLE: "1"
NCCL_MNNVL_ENABLE: "1"
NCCL_NVLS_ENABLE: "1"

decode_environment:
VLLM_USE_FLASHINFER_MOE_FP4: "1"
VLLM_USE_NCCL_SYMM_MEM: "1"
NCCL_CUMEM_ENABLE: "1"
NCCL_MNNVL_ENABLE: "1"
NCCL_NVLS_ENABLE: "1"

vllm_config:
prefill:
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
served-model-name: "nvidia/Kimi-K2.5-NVFP4"
kv-cache-dtype: "fp8"
tensor-parallel-size: 1
pipeline-parallel-size: 1
data-parallel-size: 4
data-parallel-rpc-port: 13345
enable-expert-parallel: true
max-model-len: 3072
max-num-seqs: 1024
enforce-eager: true
compilation-config: '{"custom_ops":["+quant_fp8","+rms_norm","+rotary_embedding"],"pass_config":{"fuse_attn_quant":true,"fuse_allreduce_rms":true}}'
max-num-batched-tokens: 16384
safetensors-load-strategy: "prefetch"
trust-remote-code: true
no-enable-prefix-caching: true
no-enable-chunked-prefill: true
attention-backend: "FLASHINFER_MLA"
block-size: 64
attention-config: '{"use_trtllm_ragged_deepseek_prefill": true}'
all2all-backend: "flashinfer_nvlink_one_sided"
gpu-memory-utilization: 0.9

decode:
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
served-model-name: "nvidia/Kimi-K2.5-NVFP4"
kv-cache-dtype: "fp8"
tensor-parallel-size: 4
pipeline-parallel-size: 1
enable-expert-parallel: true
max-model-len: 3072
max-num-seqs: 1024
max-num-batched-tokens: 10240
safetensors-load-strategy: "prefetch"
trust-remote-code: true
no-enable-prefix-caching: true
no-enable-chunked-prefill: true
async-scheduling: true
attention-backend: "FLASHINFER_MLA"
block-size: 64
compilation-config: '{"cudagraph_mode":"FULL_DECODE_ONLY","custom_ops":["+quant_fp8","+rms_norm","+rotary_embedding"],"pass_config":{"fuse_attn_quant":true,"fuse_allreduce_rms":true}}'
gpu-memory-utilization: 0.9
stream-interval: 50
max-cudagraph-capture-size: 1024

benchmark:
type: "sa-bench"
isl: 1024
osl: 1024
concurrencies: "4x8x16x32x64x128"
req_rate: "inf"
98 changes: 98 additions & 0 deletions recipes/vllm/kimi-k2.5/8k1k/disagg-gb200-1p4d-dep4-tep4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,98 @@
name: "kimi-vllm-disagg-gb200-1p4d-dep4-tep4"

model:
path: "kimi-k2.5-nvfp4"
container: "vllm/vllm-openai:v0.18.0-cu130"
precision: "fp4"

dynamo:
version: 1.0.1
install: true

setup_script: vllm-container-deps.sh

resources:
gpu_type: "gb200"
gpus_per_node: 4
prefill_nodes: 1
decode_nodes: 4
prefill_workers: 1
decode_workers: 4
gpus_per_prefill: 4
gpus_per_decode: 4

frontend:
type: dynamo
enable_multiple_frontends: false

backend:
type: vllm
connector: null

prefill_environment:
VLLM_USE_FLASHINFER_MOE_FP4: "1"
VLLM_USE_NCCL_SYMM_MEM: "1"
NCCL_CUMEM_ENABLE: "1"
NCCL_MNNVL_ENABLE: "1"
NCCL_NVLS_ENABLE: "1"

decode_environment:
VLLM_USE_FLASHINFER_MOE_FP4: "1"
VLLM_USE_NCCL_SYMM_MEM: "1"
NCCL_CUMEM_ENABLE: "1"
NCCL_MNNVL_ENABLE: "1"
NCCL_NVLS_ENABLE: "1"

vllm_config:
prefill:
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
served-model-name: "nvidia/Kimi-K2.5-NVFP4"
kv-cache-dtype: "fp8"
tensor-parallel-size: 1
pipeline-parallel-size: 1
data-parallel-size: 4
data-parallel-rpc-port: 13345
enable-expert-parallel: true
max-model-len: 10240
max-num-seqs: 64
enforce-eager: true
compilation-config: '{"custom_ops":["+quant_fp8","+rms_norm","+rotary_embedding"],"pass_config":{"fuse_attn_quant":true,"fuse_allreduce_rms":true}}'
max-num-batched-tokens: 16384
safetensors-load-strategy: "prefetch"
trust-remote-code: true
no-enable-prefix-caching: true
no-enable-chunked-prefill: true
attention-backend: "FLASHINFER_MLA"
block-size: 64
attention-config: '{"use_trtllm_ragged_deepseek_prefill": true}'
all2all-backend: "flashinfer_nvlink_one_sided"
gpu-memory-utilization: 0.9

decode:
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
served-model-name: "nvidia/Kimi-K2.5-NVFP4"
kv-cache-dtype: "fp8"
tensor-parallel-size: 4
pipeline-parallel-size: 1
enable-expert-parallel: true
max-model-len: 10240
max-num-seqs: 16
max-num-batched-tokens: 10240
safetensors-load-strategy: "prefetch"
trust-remote-code: true
no-enable-prefix-caching: true
no-enable-chunked-prefill: true
async-scheduling: true
attention-backend: "FLASHINFER_MLA"
block-size: 64
compilation-config: '{"cudagraph_mode":"FULL_DECODE_ONLY","custom_ops":["+quant_fp8","+rms_norm","+rotary_embedding"],"pass_config":{"fuse_attn_quant":true,"fuse_allreduce_rms":true}}'
gpu-memory-utilization: 0.9
stream-interval: 50
max-cudagraph-capture-size: 16

benchmark:
type: "sa-bench"
isl: 8192
osl: 1024
concurrencies: "4x8x16x32x128"
req_rate: "inf"
Loading
Loading