Frank
caee26e3c3
use_aux_hidden_state_outputs lives on the gpu_model_runner instance
(gpu_model_runner.py:623/678), not on the spec config, so the first
registry check never fired and the reserve stayed at 13,600 B/token.
Switch to method in {dflash, dspark, extract_hidden_states}.
32 lines
1.4 KiB
Diff
32 lines
1.4 KiB
Diff
--- a/vllm/model_executor/offloader/expert_activation_registry.py
|
|
+++ b/vllm/model_executor/offloader/expert_activation_registry.py
|
|
@@ -316,7 +316,27 @@
|
|
|
|
|
|
def _glm53_kv_bytes_per_token(cfg: "VllmConfig") -> int:
|
|
- return 13600
|
|
+ per_tok = 13600
|
|
+ # FORK-LOCAL (patches/glm53-dflash-04-kv-groups-draft): with a dflash/dspark
|
|
+ # drafter, the KV spec set gains the drafter's attention layers and the aux
|
|
+ # hidden-state cache (one bf16 hidden vector per target aux layer per
|
|
+ # token). Both are full-length per-token costs the aliased glm5 pool
|
|
+ # cannot absorb, so the reserve must include them. The drafter is a 5-layer
|
|
+ # qwen3 (8 kv heads x 128 x K+V x bf16 = 4096 B/token); the aux count is
|
|
+ # the dflash target_layer_ids count (5).
|
|
+ # NOTE: use_aux_hidden_state_outputs lives on the gpu_model_runner
|
|
+ # instance (gpu_model_runner.py:623/678), not on the spec config -- it is
|
|
+ # not set yet when the expert plan runs. The spec-config METHOD is the
|
|
+ # plan-time signal for the same fact.
|
|
+ sc = getattr(cfg, "speculative_config", None)
|
|
+ if sc is not None and getattr(sc, "method", "") in (
|
|
+ "dflash",
|
|
+ "dspark",
|
|
+ "extract_hidden_states",
|
|
+ ):
|
|
+ hidden = int(cfg.model_config.hf_config.hidden_size)
|
|
+ per_tok += 5 * hidden * 2 + 4096
|
|
+ return per_tok
|
|
|
|
|
|
for _arch in ("Glm5NextForConditionalGeneration", "Glm5NextForCausalLM"):
|