MOVZXandHinata 41f6691c26 [Qwen4Exp] Host-resident token embedding tables (VLLM_HOST_EMBED_TABLE) ...

Keeps the token embedding table in pinned host memory behind a UVA view for the
stage-0 target and the last-stage MTP drafter, freeing GPU memory for KV. TP
sharding, masking and the all-reduce are retained. The knob is registered as a
compile-cache factor.

Co-Authored-By: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>

2026-10-09 19:43:53 +07:00

..

common

[5/N][warmup][DSv4] Migrate NVIDIA CuTeDSL attention kernels (#53566)

2026-09-12 00:05:59 -04:00

deepseek_v4

[Bugfix][XPU] Make DeepSeek V4 FP8 sparse decode graph-capturable (#59159)

2026-10-04 18:31:15 +08:00

deepseek_v32

[Perf][PCP] Shard decode requests across PCP ranks (#52162)

2026-10-01 23:50:13 -04:00

deepseek_v41

[Bugfix][DSv4.1] Keep the compressor ring out of the null block (#58560)

2026-10-05 01:49:41 +00:00

dots3_note

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

glm5next

[Bugfix][Multimodal] Fix GLM-5.3-Flash vision tower crashes on image input (#59126)

2026-10-02 15:25:37 +00:00

hy_v4

[CI] Bump Transformers version to 5.18.0 (#59621)

2026-10-04 00:42:35 +00:00

inkling

[Bugfix][Spec Decode] Per-module LM heads for multi-layer MTP on Model Runner V2 (#58921)

2026-10-01 01:09:14 -07:00

kimi_k3

Merge remote-tracking branch 'upstream/main' into patches

2026-10-03 21:59:03 +07:00

minimax_m3

[Minimax-M3] Keep the native FP8 MMA in the Triton indexer scorers (#59481)

2026-10-02 12:30:39 -04:00

qwen4_exp

[Qwen4Exp] Host-resident token embedding tables (VLLM_HOST_EMBED_TABLE)

2026-10-09 19:43:53 +07:00

__init__.py

[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (#43004)

2026-05-18 19:50:02 -07:00