minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

[Docs] Muse Glimmer cookbook: drop --speculative-dflash-block-size 5 (#34323)

Browse Source 
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
This commit is contained in:
Brayden Zhong
2026-08-10 15:46:34 -07:00
committed by GitHub
co-authored by Brayden Zhong
parent 2c72323d90
commit b86c90215f
1 changed files with 1 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/src/snippets/configs/meta-models/muse-glimmer.jsx
+1 -11
View File
@@ -127,8 +127,7 @@ export const config = {
{ id: "off", label: "Off" }, { id: "off", label: "Off" },
{ id: "dflash", label: "DFlash", { id: "dflash", label: "DFlash",
flags: ["--speculative-algorithm DFLASH", flags: ["--speculative-algorithm DFLASH",
"--speculative-draft-model-path {{DRAFT_PATH}}", "--speculative-draft-model-path {{DRAFT_PATH}}"] },
"--speculative-dflash-block-size 5"] },
], ],
}, },
}, },
@@ -164,7 +163,6 @@ export const config = {
"--speculative-algorithm DFLASH", "--speculative-algorithm DFLASH",
"--speculative-draft-model-path {{DRAFT_PATH}}", "--speculative-draft-model-path {{DRAFT_PATH}}",
"--speculative-draft-load-format auto", "--speculative-draft-load-format auto",
"--speculative-dflash-block-size 5",
"--mem-fraction-static 0.85", "--mem-fraction-static 0.85",
"--host {{HOST_IP}}", "--host {{HOST_IP}}",
"--port {{PORT}}", "--port {{PORT}}",
@@ -214,7 +212,6 @@ export const config = {
"--tool-call-parser muse", "--tool-call-parser muse",
"--speculative-algorithm DFLASH", "--speculative-algorithm DFLASH",
"--speculative-draft-model-path {{DRAFT_PATH}}", "--speculative-draft-model-path {{DRAFT_PATH}}",
"--speculative-dflash-block-size 5",
"--speculative-draft-model-quantization fp8", "--speculative-draft-model-quantization fp8",
"--kv-cache-dtype fp8_e4m3", "--kv-cache-dtype fp8_e4m3",
"--mem-fraction-static 0.9", "--mem-fraction-static 0.9",
@@ -246,7 +243,6 @@ export const config = {
"--tool-call-parser muse", "--tool-call-parser muse",
"--speculative-algorithm DFLASH", "--speculative-algorithm DFLASH",
"--speculative-draft-model-path {{DRAFT_PATH}}", "--speculative-draft-model-path {{DRAFT_PATH}}",
"--speculative-dflash-block-size 5",
"--mem-fraction-static 0.85", "--mem-fraction-static 0.85",
"--host {{HOST_IP}}", "--host {{HOST_IP}}",
"--port {{PORT}}", "--port {{PORT}}",
@@ -286,7 +282,6 @@ export const config = {
"--tool-call-parser muse", "--tool-call-parser muse",
"--speculative-algorithm DFLASH", "--speculative-algorithm DFLASH",
"--speculative-draft-model-path {{DRAFT_PATH}}", "--speculative-draft-model-path {{DRAFT_PATH}}",
"--speculative-dflash-block-size 5",
"--speculative-draft-model-quantization fp8", "--speculative-draft-model-quantization fp8",
"--kv-cache-dtype fp8_e4m3", "--kv-cache-dtype fp8_e4m3",
"--mem-fraction-static 0.85", "--mem-fraction-static 0.85",
@@ -322,7 +317,6 @@ export const config = {
"--tool-call-parser muse", "--tool-call-parser muse",
"--speculative-algorithm DFLASH", "--speculative-algorithm DFLASH",
"--speculative-draft-model-path {{DRAFT_PATH}}", "--speculative-draft-model-path {{DRAFT_PATH}}",
"--speculative-dflash-block-size 5",
"--mem-fraction-static 0.65", "--mem-fraction-static 0.65",
"--host {{HOST_IP}}", "--host {{HOST_IP}}",
"--port {{PORT}}", "--port {{PORT}}",
@@ -362,7 +356,6 @@ export const config = {
"--tool-call-parser muse", "--tool-call-parser muse",
"--speculative-algorithm DFLASH", "--speculative-algorithm DFLASH",
"--speculative-draft-model-path {{DRAFT_PATH}}", "--speculative-draft-model-path {{DRAFT_PATH}}",
"--speculative-dflash-block-size 5",
"--speculative-draft-model-quantization fp8", "--speculative-draft-model-quantization fp8",
"--kv-cache-dtype fp8_e4m3", "--kv-cache-dtype fp8_e4m3",
"--mem-fraction-static 0.38", "--mem-fraction-static 0.38",
@@ -394,7 +387,6 @@ export const config = {
"--tool-call-parser muse", "--tool-call-parser muse",
"--speculative-algorithm DFLASH", "--speculative-algorithm DFLASH",
"--speculative-draft-model-path {{DRAFT_PATH}}", "--speculative-draft-model-path {{DRAFT_PATH}}",
"--speculative-dflash-block-size 5",
"--mem-fraction-static 0.85", "--mem-fraction-static 0.85",
"--host {{HOST_IP}}", "--host {{HOST_IP}}",
"--port {{PORT}}", "--port {{PORT}}",
@@ -470,7 +462,6 @@ export const config = {
"--tool-call-parser muse", "--tool-call-parser muse",
"--speculative-algorithm DFLASH", "--speculative-algorithm DFLASH",
"--speculative-draft-model-path {{DRAFT_PATH}}", "--speculative-draft-model-path {{DRAFT_PATH}}",
"--speculative-dflash-block-size 5",
"--mem-fraction-static 0.85", "--mem-fraction-static 0.85",
"--host {{HOST_IP}}", "--host {{HOST_IP}}",
"--port {{PORT}}", "--port {{PORT}}",
@@ -510,7 +501,6 @@ export const config = {
"--tool-call-parser muse", "--tool-call-parser muse",
"--speculative-algorithm DFLASH", "--speculative-algorithm DFLASH",
"--speculative-draft-model-path {{DRAFT_PATH}}", "--speculative-draft-model-path {{DRAFT_PATH}}",
"--speculative-dflash-block-size 5",
"--speculative-draft-model-quantization fp8", "--speculative-draft-model-quantization fp8",
"--kv-cache-dtype fp8_e4m3", "--kv-cache-dtype fp8_e4m3",
"--mem-fraction-static 0.85", "--mem-fraction-static 0.85",