Neal Vaidyaandishandhanani f1ff697494 add hybrid model PD to NIXL connector (#16229) ...

Signed-off-by: Neal Vaidya <nealv@nvidia.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>

2026-02-06 15:05:36 -08:00

..

ascend

[NPU] disaggregation_decode_enable_fake_auto parameter adaptation (#17811)

2026-02-01 18:14:26 +08:00

base

Support PD disaggregation with different TP/DP size for Qwen3-Next (#16056)

2026-01-25 15:34:02 +08:00

common

[NPU] disaggregation_decode_enable_fake_auto parameter adaptation (#17811)

2026-02-01 18:14:26 +08:00

fake

[PD] Add PD support for hybrid model (Qwen3-Next, DeepSeek V3.2 Exp) (#10912)

2025-10-15 18:59:14 -07:00

mooncake

[PD] Minor code cleanup for mooncake backend (#18279)

2026-02-05 17:38:09 +08:00

mori

[PD] Support KV transfer with MORI-IO (#14626)

2026-01-28 23:22:41 -08:00

nixl

add hybrid model PD to NIXL connector (#16229)

2026-02-06 15:05:36 -08:00

decode_kvcache_offload_manager.py

[Fix] data race in req_to_token pool (#17850)

2026-02-02 14:38:15 -08:00

decode_schedule_batch_mixin.py

Adjust wrong mtp meaning introduce by mimo (#15632)

2025-12-23 02:06:46 +08:00

decode.py

[Fix] data race in req_to_token pool (#17850)

2026-02-02 14:38:15 -08:00

encode_receiver.py

fix: zmq_to_tokenizer encoder transfer when host listens to 0.0.0.0 (#17929)

2026-02-02 13:27:27 +08:00

encode_server.py

[EPD][Perf] parallelize ZMQ send for encode server (#16487)

2026-01-31 14:30:11 +08:00

kv_events.py

fix(tcp-port): replace bind_server_socket to get_zmq_socket(Port conflict) (#11961)

2025-11-12 18:05:16 +08:00

prefill.py

[Fix] data race in req_to_token pool (#17850)

2026-02-02 14:38:15 -08:00

utils.py

[PD] feat: support mooncake intra-node nvlink kv transfer (#17866)

2026-02-03 17:47:52 +08:00